IMAGE PROCESSING DEVICE, METHOD, AND PROGRAM CROSS-REFERENCE TO RELATED APPLICATION This application claims priority of Japanese Patent Application No. 2010-183877, filed on August 19, 2010, the entire content of which is hereby incorporated by reference. BACKGROUND The present disclosure relates to an image processing device and an image processing method, and a program, and in particular, the present disclosure relates to an image processing device and an image processing method, and a program, which are capable of classifying the composition of an input image. In recent years, there has been a technology capable of discriminating a composition pattern of an image captured by an imaging device such as a digital camera or the like. For example, there has been a technology that recognizes an attention subject, recognizes the state of the attention subject, and selects a composition pattern including the attention subject from among a plurality of recorded composition patterns, on the basis of the recognized state of the attention subject. For example, an example of such a technology is disclosed in Japanese Unexamined Patent Application Publication No. 2008-81246. In addition, there has been proposed an image processing device that detects a characteristic pattern by analyzing an input image, calculates, as an evaluation value, the degree of association between a plurality of preliminarily prepared compositions and the detected characteristic pattern, and determines the composition of the input image on the basis of the evaluation value. For example, an example of such an image processing device is disclosed in Japanese Unexamined Patent Application Publication No. 2009-159023. Furthermore, there has been proposed a camera that extracts an edge corresponding to the upper end of a main subject in a captured image or an edge extending between two corresponding sides of a captured image, compares the position or the inclination of the extracted edge with a preliminarily defined appropriate range, and determines whether a composition is right or wrong. For example, an example of such an image processing device is disclosed in Japanese Patent No. 4029174. SUMMARY However, in the method of Japanese Unexamined Patent Application Publication No. 2008-81246, a high-cost operation has been necessary for recognizing a subject or recognizing the state of the attention subject. In addition, in the method of Japanese Unexamined Patent Application Publication No. 2009-159023, since an evaluation value between a plurality of preliminarily prepared compositions and a characteristic pattern detected on the basis of the analysis of an input image is calculated with respect to each of pixels, a high-cost operation has also been necessary. Furthermore, in the method of Japanese Patent No. 4029174, since a decision criterion for determining whether a composition is right or wrong is only based on an edge corresponding to the upper end of a main subject in a captured image or an edge extending between two corresponding sides of a captured image, the type of composition to be determined has been limited. The present disclosure addresses the above-mentioned problems. In addition, it is desirable to classify the composition of an input image into detailed composition patterns with a lower-cost operation. Accordingly, there is disclosed a device for processing an input image. The device may include a degree-of-symmetry calculation unit, which may be configured to receive the input image and calculate a degree of symmetry of the input image. The device may also include a parting line detection unit, which may be configured to receive the input image and detect a parting line that separates two sides of the input image. Additionally, the device may include a classification unit, which may be configured to classify the input image based on the degree of symmetry and the parting line. The classification unit may also be configured to generate a classification signal to cause at least one of display or storage of the classification. There is also disclosed a method of processing an input image. A processor may execute a program to cause a device to perform the method. The program may be stored on a non-transitory, computer-readable storage medium. The method may include receiving the input image. Additionally, the method may include calculating a degree of symmetry of the input image. The method may also include detecting a parting line that separates two sides of the input image. In addition, the method may include classifying the input image based on the degree of symmetry and the parting line. The method may also include generating a classification signal to cause at least one of display or storage of the classification. BRIEF DESCRIPTION OF THE DRAWINGS Fig. 1 is a block diagram illustrating an example of a functional configuration of an image processing device according to an embodiment of the presently disclosed technology; Fig. 2 is a block diagram illustrating an example of a functional configuration of a degree-of-symmetry calculation unit (i.e., a software module, a hardware module, or a combination of a software module and a hardware module); Fig. 3 is a block diagram illustrating an example of a functional configuration of a degree-of-edge-symmetry calculation unit; Fig. 4 is a block diagram illustrating an example of a functional configuration of a degree-of-color-symmetry calculation unit; Fig. 5 is a block diagram illustrating an example of a functional configuration of a parting line detection unit; Fig. 6 is a block diagram illustrating an example of a functional configuration of a horizontal parting line detection unit; Fig. 7 is a block diagram illustrating an example of a functional configuration of a vertical parting line detection unit; Fig. 8 is a block diagram illustrating an example of a functional configuration of an oblique parting line detection unit; Fig. 9 is a flowchart explaining composition classification processing; Fig. 10 is a diagram explaining a composition pattern usually recommended in a photo shoot or the like; Fig. 11 is a flowchart explaining degree-of-symmetry-calculation processing; Fig. 12 is a flowchart explaining degree-of-edge-symmetry calculation processing; Fig. 13 is a diagram explaining an input image and an edge image; Fig. 14 is a diagram explaining an example of calculation of a degree of edge left-right symmetry; Fig. 15 is a diagram explaining an example of calculation of a degree of edge up-down symmetry; Fig. 16 is a diagram explaining an input image and an edge image; Fig. 17 is a flowchart explaining degree-of-color-symmetry calculation processing; Fig. 18 is a diagram explaining a weighting coefficient based on a color difference; Fig. 19 is a diagram explaining the conversion of the sum of color differences; Fig. 20 is a flowchart explaining parting line detection processing; Fig. 21 is a diagram explaining an input image and an edge image; Fig. 22 is a flowchart explaining horizontal parting line detection processing; Fig. 23 is a diagram explaining an integration value in a horizontal direction of edge information; Fig. 24 is a diagram explaining an example of a detection result of a horizontal parting line; Fig. 25 is a flowchart explaining vertical parting line detection processing; Fig. 26 is a diagram explaining an integration value in a vertical direction of edge information; Fig. 27 is a flowchart explaining oblique parting line detection processing; Fig. 28 is a diagram explaining an input image and an edge image, the binarization of the edge image, and the rotation of the edge image; Fig. 29 is a diagram explaining an example of the normalization of an integration value of edge information of each line in ah oblique direction; Fig. 30 is a diagram explaining an example of the normalization of an integration value of edge information of each line in an oblique direction; Fig. 31 is a diagram explaining an integration value in an oblique direction of edge information; Fig. 32 is a diagram explaining an example of a detection result of an oblique parting line; Fig. 33 is a diagram explaining another example of the normalization of an integration value of edge information of each line in an oblique direction; Fig. 34 is a diagram explaining another example of the normalization of an integration value of edge information of each line in an oblique direction; Fig. 35 is a diagram explaining another example of the normalization of an integration value of edge information of each line in an oblique direction; Fig. 36 is a diagram explaining an example of a composition pattern into which a composition of an input image is classified; Fig. 37 is a diagram explaining an example of a composition pattern classified on the basis of a horizontal parting line; Fig. 38 is a diagram explaining an example of a composition pattern classified on the basis of a vertical parting line; Figs. 39A and 39B are diagrams explaining examples of a composition pattern classified on the basis of an oblique parting line; Fig. 40 is a diagram explaining an example of a composition pattern classified on the basis of an oblique parting line; Fig. 41 is a diagram illustrating a relationship between a degree of symmetry and a parting line; Fig. 42 is a flowchart explaining another operation of composition classification processing; Fig. 43 is a block diagram illustrating an example of a functional configuration of an imaging device; Fig. 44 is a diagram explaining a display example of the recommendation of composition; Fig. 45 is a diagram explaining a display example of the recommendation of composition; and Fig. 4 6 is a block diagram illustrating an example of a configuration of computer hardware. DETAILED DESCRIPTION OF EMBODIMENTS Hereinafter, embodiments of the presently disclosed technology will be described with reference to figures. [Example of Configuration on Image Processing Device] Fig. 1 illustrates an example of the functional configuration of an image processing device according to an embodiment of the presently disclosed technology. For example, an image processing device 11 in Fig. 1 calculates the degree of symmetry indicating the line symmetry of an input image input from an imaging device such as a digital camera or the like or another image processing device, and detects a parting line partitioning the input image into predetermined domains. In addition, the image processing device 11 classifies the composition of the input image into predetermined composition patterns (i.e., classifications) on the basis of at least one of the degree of symmetry and the parting line. The image processing device 11 includes a degree-of-symmetry calculation unit 31, a parting line detection unit 32, and a composition classification unit 33. The input image input to the image processing device 11 is supplied to the degree-of-symmetry calculation unit 31 and the parting line detection unit 32. The degree-of-symmetry calculation unit 31 calculates the degree of symmetry indicating the line symmetry of the pixel information (pixel value) of each of pixels in the input image, with respect to each of the left-right direction and the up-down direction of the input image, and supplies the degree of symmetry to the composition classification unit 33. [Example of Functional Configuration of Degree-of-Symmetry Calculation Unit] Fig. 2 illustrates an example of the functional configuration of the degree-of-symmetry calculation unit 31. The degree-of-symmetry calculation unit 31 includes a degree-of-edge-symmetry calculation unit 41, a degree-of-color-symmetry calculation unit 42, and a degree-of-symmetry determination unit 43. The degree-of-edge-symmetry calculation unit 41 calculates the degree of symmetry (hereinafter, referred to as the degree of edge symmetry) of edge information that is a type of pixel information of each of pixels in the input image, and supplied the degree of symmetry to the degree-of-symmetry determination unit 43. [Example of Functional Configuration of Degree-of-Edge-Symmetry Calculation Unit] Fig. 3 illustrates an example of the functional configuration of the degree-of-edge-symmetry calculation unit 41. The degree-of-edge-symmetry calculation unit 41 includes an edge image generation unit 51, a degree-of-left-right-symmetry calculation unit 52 (i.e., a first degree-of-edge-symmetry calculation unit), and a degree-of-up-down-symmetry calculation unit 53 (i.e., a second degree-of-edge-symmetry calculation unit). The edge image generation unit 51 generates an edge image including the edge information of each of pixels in the input image (i.e., an edge image that indicates edges of the input image), on the basis of each of the pixels, and supplies the edge image to the degree-of-left-right-symmetry calculation unit 52 and the degree-of-up-down-symmetry calculation unit 53. The degree-of-left-right-symmetry calculation unit 52 calculates the degree of edge left-right symmetry that is the degree of symmetry of edge information, with respect to a center line in a left-right direction in the edge image (i.e., a first imaginary line in the edge image that is parallel to a side of the edge image) supplied from the edge image generation unit 51, and outputs the degree of edge left-right symmetry. The degree-of-up-down-symmetry calculation unit 53 calculates the degree of edge up-down symmetry that is the degree of symmetry of edge information, with respect to a center line in an up-down direction in the edge image (i.e., a second imaginary line in the edge image that is perpendicular to the first imaginary line) supplied from the edge image generation unit 51, and outputs the degree of edge up-down symmetry. In this way, the degree-of-edge-symmetry calculation unit 41 supplies, as the degree of edge symmetry, the degree of edge left-right symmetry and the' degree of edge up-down symmetry to the degree-of-symmetry determination unit 43. Returning to the description of Fig. 2, the degree-of-color-symmetry calculation unit 42 calculates the degree of symmetry (hereinafter, referred to as the degree of color symmetry) of color information that is a type of pixel information of each of pixels in the input image, and supplied the degree of symmetry to the degree-of-symmetry determination unit 43. [Example of Functional Configuration of Degree-of-Color-Symmetry Calculation Unit] Fig. 4 illustrates an example of the functional configuration of the degree-of-color-symmetry calculation unit 42. The degree-of-color-symmetry calculation unit 42 includes a color space conversion unit 61, a degree-of-left-right-symmetry calculation unit 62 (i.e., a first degree-of-color-symmetry calculation unit), and a degree-of-up-down-symmetry calculation unit 63 (i.e., a second degree-of-color-symmetry calculation unit). The color space conversion unit 61 converts, into another color space, a color space in which the pixel information (color information) of each of pixels in the input image is represented, and supplies, to the degree-of-left-right-symmetry calculation unit 62 and the degree-of-up-down-symmetry calculation unit 63, the input image including color information represented in the converted color space. The degree-of-left-right-symmetry calculation unit 62 calculates the degree of color left-right symmetry that is the degree of symmetry of color information, with respect to a center line in a left-right direction in the input image (i.e., a first imaginary line in the input image that is parallel to a side of the input image) supplied from the color space conversion unit 61, and outputs the degree of color left-right symmetry. The degree-of-up-down-symmetry calculation unit 63 calculates the degree of color up-down symmetry that is the degree of symmetry of color information, with respect to a center line in an up-down direction in the input image (i.e., a second imaginary line in the input image that is perpendicular to the first imaginary line) supplied from the color space conversion unit 61, and outputs the degree of color up-down symmetry. In this way, the degree-of-color-symmetry calculation unit 42 supplies, as the degree of color symmetry, the degree of color left-right symmetry and the degree of color up-down symmetry to the degree-of-symmetry determination unit 43. Returning to the description of Fig. 2, on the basis of the degree of edge symmetry supplied from the degree-of-edge-symmetry calculation unit 41 and the degree of color symmetry supplied from the degree-of-color-symmetry calculation unit 42, the degree-of-symmetry determination unit 43 determines the degree of left-right symmetry indicating line symmetry with respect to the left-right direction of the input image and the degree of up-down symmetry indicating line symmetry with respect to the up-down direction of the input image. Specifically, the degree-of-symmetry determination unit 43 determines, as the degree of left-right symmetry, one of the degree of edge left-right symmetry supplied, as the degree of edge symmetry, from the degree-of-edge-symmetry calculation unit 41 and the degree of color left-right symmetry supplied, as the degree of color symmetry, from the degree-of-color-symmetry calculation unit 42, the determined one satisfying a predetermined condition. In addition, the degree-of-symmetry determination unit 43 determines, as the degree of up-down symmetry, one of the degree of edge up-down symmetry supplied, as the degree of edge symmetry, from the degree-of-edge-symmetry calculation unit 41 and the degree of color up-down symmetry supplied, as the degree of color symmetry, from the degree-of-color-symmetry calculation unit 42, the determined one satisfying a predetermined condition. In this way, the degree-of-symmetry calculation unit 31 supplies, as the degree of symmetry, the degree of left-right symmetry and the degree of up-down, symmetry to the composition classification unit 33. Returning to the description of Fig. 1, the parting line detection unit 32 detects a parting line for partitioning the input image, from a variation in the distribution of pixel information in the input image, and supplies parting line information indicating the detected parting line to the composition classification unit 33. [Example of Functional Configuration of Parting Line Detection Unit] Fig. 5 illustrates an example of the functional configuration of the parting line detection unit 32. The parting line detection unit 32 includes an edge image generation unit 71, a horizontal parting line detection unit 72 (i.e., a first parting line detection unit), a vertical parting line detection unit 73 (i.e., a second parting line detection unit), and oblique parting line detection units 74 and 75 (i.e., third and fourth parting line detection units). In the same way as the edge image generation unit 51 in Fig. 3, the edge image generation unit 71 generates an edge image including the edge information of each of pixels in the input image, on the basis of each of the pixels, and supplies the edge image to the horizontal parting line detection unit 72 to the oblique parting line detection unit 75. The horizontal parting line detection unit 72 integrates the edge information in a horizontal direction in the edge image supplied from the edge image generation unit 71, and detects a horizontal parting line (i.e., a first parting line) partitioning the input image in the horizontal direction (namely, into up and down), from the distribution of the integration value thereof. The horizontal parting line detection unit 72 outputs horizontal parting line information indicating the detected horizontal parting line. The vertical parting line detection unit 73 integrates the edge information in a vertical direction in the edge image supplied from the edge image generation unit 71, and detects a vertical parting line (i.e., a second parting line that is angled with respect to the first parting line) partitioning the input image in the vertical direction (namely, into right and left), from the distribution of the integration value thereof. The vertical parting line detection unit 73 outputs vertical parting line information indicating the detected vertical parting line. The oblique parting line detection unit 74 integrates the edge information in an upper right oblique direction in the edge image supplied from the edge image generation unit 71, and detects an upper right oblique parting line (i.e., a third parting line that is angled with respect to the first and second parting lines) partitioning the input image in the upper right oblique direction, from the distribution of the integration value thereof. The oblique parting line detection unit 74 outputs first oblique parting line information indicating the detected upper right oblique parting line. The oblique parting line detection unit 75 integrates the edge information in an upper left oblique direction in the edge image supplied from the edge image generation unit 71, and detects an upper left oblique parting line (i.e., a fourth parting line that is angled with respect to the first, second, and third parting lines) partitioning the input image in the upper left oblique direction, from the distribution of the integration value thereof. The oblique parting line detection unit 75 outputs second oblique parting line information indicating the detected upper left oblique parting line. In this way, as the parting line information, the parting line detection unit 32 supplies the horizontal parting line information, the vertical parting line information, the first oblique parting line information, and the second oblique parting line information to the composition classification unit 33. Here, with reference to Figs. 6 to 8, examples of the functional configurations of the horizontal parting line detection unit 72 to the oblique parting line detection unit 75 are illustrated. [Example of Functional Configuration of Horizontal Parting Line Detection Unit] Fig. 6 illustrates an example of the functional configuration of the horizontal parting line detection unit 72. The horizontal parting line detection unit 72 includes a horizontal direction integration unit 111, a low pass filter (LPF) 112, a peak value detection unit 113, and a threshold value processing unit 114. The horizontal direction integration unit 111 integrates the pixel information (edge information) of a pixel, with respect to each of lines including pixels (hereinafter, simply referred to as line) in the horizontal direction in the edge image supplied from the edge image generation unit 71, and supplies the integration result thereof to the LPF 112. The integration result obtained here is the integration value of the edge information in the horizontal direction, with respect to a pixel position in the vertical direction in the edge image (input image). By performing filtering processing on the integration result from the horizontal direction integration unit 111, namely, the integration value of the edge information in the horizontal direction with respect to a pixel position in the vertical direction in the edge image, the LPF 112 removes noise from the integration result, and supplies the integration result to the peak value detection unit 113. The peak value detection unit 113 detects the peak value of the integration value from the integration result from which noise is removed by the LPF 112, and supplies to the threshold value processing unit 114 the detected peak value and the pixel position in the vertical direction of the line in the horizontal direction from which the integration value to be the peak value is obtained. The threshold value processing unit 114 compares the peak value from the peak value detection unit 113 with a predetermined threshold value. In addition, when the peak value is greater than the predetermined threshold value, the threshold value processing unit 114 defines, as the horizontal parting line, the line in the horizontal direction from which the integration value to be the peak value is obtained, and outputs, as the horizontal parting line information, the pixel position in the vertical direction of the line in the edge image. [Example of Functional Configuration of Vertical Parting Line Detection Unit] Fig. 7 illustrates an example of the functional configuration of the vertical parting line detection unit 73. The vertical parting line detection unit 73 includes a vertical direction integration unit 121, an LPF 122, a peak value detection unit 123, and a threshold value processing unit 124. The vertical direction integration unit 121 integrates the edge information with respect to each of lines in the vertical direction in the edge image supplied from the edge image generation unit 71, and supplies the integration result thereof to the LPF 122. The integration result obtained here is the integration value of the edge information in the vertical direction, with respect to a pixel position in the horizontal direction in the edge image (input image). By performing filtering processing on the integration result from the vertical direction integration unit 121, namely, the integration value of the edge information in the vertical direction with respect to a pixel position in the horizontal direction in the edge image, the LPF 122 removes noise from the integration result, and supplies the integration result to the peak value detection unit 123. The peak value detection unit 123 detects the peak value of the integration value from the integration result from which noise is removed by the LPF 122, and supplies to the threshold value processing unit 124 the detected peak value and the pixel position in the horizontal direction of the line in the vertical direction from which the integration value to be the peak value is obtained. The threshold value processing unit 124 compares the peak value from the peak value detection unit 123 with a predetermined threshold value. In addition, when the peak value is greater than the predetermined threshold value, the threshold value processing unit 124 defines, as the vertical parting line, the line in the vertical direction from which the integration value to be the peak value is obtained, and outputs, as the vertical parting line information, the pixel position in the horizontal direction of the line in the edge image. [Example of Functional Configuration of Oblique Parting Line Detection Unit] Fig. 8 illustrates an example of the functional configuration of the oblique parting line detection unit 74. The oblique parting line detection unit 74 includes an oblique direction integration unit 131, an LPF 132, a peak value detection unit 133, and a threshold value processing unit 134. The oblique direction integration unit 131 integrates the edge information, with respect to each of lines in the upper right oblique direction in the edge image supplied from the edge image generation unit 71, and supplies the integration result thereof to the LPF 132. The integration result obtained here is the integration value of the edge information in the upper right oblique direction, with respect to a pixel position in the upper left oblique direction in the edge image (input image). By performing filtering processing on the integration result from the oblique direction integration unit 131, namely, the integration value of the edge information in the upper right oblique direction with respect to a pixel position in the upper left oblique direction in the edge image, the LPF 132 removes noise from the integration result, and supplies the integration result to the peak value detection unit 133. The peak value detection unit 133 detects the peak value of the integration value from the integration result from which noise is removed by the LPF 132, and supplies to the threshold value processing unit 134 the detected peak value and the pixel position in the upper left oblique direction of the line in the upper right oblique direction from which the integration value to be the peak value is obtained. The threshold value processing unit 134 compares the peak value from the peak value detection unit 133 with a predetermined threshold value. In addition, when the peak value is greater than the predetermined threshold value, the threshold value processing unit 114 defines, as the upper right oblique parting line, the line in the upper right oblique from which the integration value to be the peak value is obtained, and outputs, as first parting line information, the pixel position in the upper left oblique direction of the line in the edge image. In addition, an example of the functional configuration of the oblique parting line detection unit 7 5 is basically the same as that of the oblique parting line detection unit 74 in Fig. 8, with the exception that, in individual units of the oblique parting line detection unit 74, processing for the upper right oblique direction of the edge information is replaced with processing for the upper left oblique direction of the edge information. Therefore, the description thereof will be omitted. In addition, returning to the description of Fig. 1, the composition classification unit 33 classifies the composition of the input image into one of preliminarily defined composition patterns, on the basis of the degree of symmetry from the degree-of-symmetry calculation unit 31 and the parting line information from the parting line detection unit 32, and outputs the composition pattern, along with the degree of symmetry and the parting line information, to an information processing device, a storage device, or the like, not illustrated. [Composition Classification Processing Performed in Image Processing Device] Next, composition classification processing performed in the image processing device 11 in Fig. 1 will be described with reference to a flowchart in Fig. 9. The composition of an input image input to the image processing device 11 is classified into one of preliminarily defined composition patterns, on the basis of composition classification processing illustrated in the flowchart in Fig. 9. Here, a composition pattern usually recommended in a photo shoot or the like will be described with reference to Fig. 10. A composition pattern C illustrated in Fig. 10 includes two representative composition patterns such as composition based on the Rule of Thirds and diagonal composition. The composition based on the Rule of Thirds is composition including horizontal parting lines HI and H2 and vertical parting lines VI and V2, called tripartition lines. In addition, the boundary of a subject or a landscape is positioned on at least one line of the horizontal parting lines HI and H2 and the vertical parting lines VI and V2, or a subject is positioned at one of four intersection points (tripartition line intersection points) between the horizontal parting lines HI and H2 and the vertical parting lines VI and V2, thereby allowing a well-balanced image to be obtained. In addition, the diagonal composition is composition including diagonal lines Dl and D2, and the boundary of a subject or a landscape is positioned on at least one line of the diagonal lines Dl and D2, thereby allowing a well-balanced image to be obtained. In the composition classification processing described hereinafter, it is determined how symmetric the composition of an input image is with respect to a left-right direction or an up-down direction or which of the above-mentioned composition based on the Rule of Thirds or diagonal composition the composition of an input image is similar to. In Step S11 in the flowchart in Fig. 9, the degree-of-symmetry calculation unit 31 executes degree-of-symmetry calculation processing, and calculates the degree of symmetry of the pixel information of each of pixels in the input image, with respect to each of the left-right direction and the up-down direction of the input image. [Degree-of-Symmetry Calculation Processing Performed in Degree-of-Symmetry Calculation Unit] Here, the degree-of-symmetry calculation processing performed in Step Sll in the flowchart in Fig. 9 will be described with reference to a flowchart in Fig. 11. In Step S31, the degree-of-edge-symmetry calculation unit 41 in the degree-of-symmetry calculation unit 31 executes degree-of-edge-symmetry calculation processing, and calculates the degree of edge symmetry of the input image. [Degree-of-Edge-Symmetry Calculation Processing Performed in Degree-of-Edge-Symmetry Calculation Unit] Here, the degree-of-edge-symmetry calculation processing performed in Step S31 in the flowchart in Fig. 11 will be described with reference to a flowchart in Fig. 12. In Step S41, the edge image generation unit 51 in the degree-of-edge-symmetry calculation unit 41 acquires a luminance image from the input image, and generates an edge image that includes an edge value (edge information) obtained by applying an edge extraction filter such as a Sobel filter, a Gabor filter, or the like to the luminance image. In addition, the edge image generation unit 51 may acquire color channel images such as R, G, B and the like from the input image, compare edge values, obtained by individually applying the edge extraction filter to the color channel images, with one another between channels with respect to each pixel, and generate an edge image including individual maximum values. Furthermore, the edge image generation unit 51 may also perform the region partitioning of a color, which utilizes a mean shift algorithm (Mean Shift method) or the like, on the input image, and generate an edge image by assigning an edge value to a pixel on the boundary line of a partitioned region. For example, in this case, an edge value "1" is assigned to a pixel on the boundary line of a region, and an edge value "0" is assigned to a pixel in a region other than the boundary line. For example, when, as illustrated in Fig. 13, a scenery image in which a subject is a mountain is input as an input image PI, the edge image generation unit 51 generates an edge image Pie that indicates the profile shape of a scene including the mountain. The edge image Pie generated in this way is supplied to the degree-of-left-right-symmetry calculation unit 52 and the degree-of-up-down-symmetry calculation unit 53. In Step S42, the degree-of-left-right-symmetry calculation unit 52 calculates the degree of edge left-right symmetry that is the degree of left-right symmetry of the edge image, on the basis of the edge image supplied from the edge image generation unit 51. Here, an example of the calculation of the degree of edge left-right symmetry will be described with reference to Fig. 14. Fig. 14 illustrates the edge image Pie. As illustrated in Fig. 14, if the edge image Pie includes H x W pixels, a center line in a left-right direction in the edge image Pie is a line located at a pixel position W / 2. In addition, attention is focused on a line in the horizontal direction, the pixel position in an up-down direction of which is "i", and it is assumed that the pixel position of a pixel located j pixels away on the right side from a pixel (a pixel whose pixel position is W / 2) on the center line in the left-right direction is represented by "+ j" and the pixel position of a pixel located j pixels away on the left side from the pixel on the center line in the horizontal direction is represented by "- j". At this time, in the edge image Pie, the sum d of a difference between pieces of edge information of a pair of pixels located on opposite sides of the center line in the left-right direction (the pixel position thereof is W / 2), the pixel positions of the pair of pixels being pixel positions (i, j) and (i, - j) (hereinafter, simply referred to as pixel position (i, j)), and the sum s of pieces of edge information of the pairs of pixels located on opposite sides of the center line in the left-right direction (namely, the sum of pieces of edge information of all pixels) are indicated by the following Expressions (1) and (2), respectively. In Expressions (1) and (2), a coefficient w is a weighting coefficient whose weighting decreases with an increase in the distance of the pixel position (i, j) of an attention pixel from the center point of the input image, the pixel position (i, j) being defined with respect to the center of the edge image, and when the distance of the pixel position (i, j) from the center point of the input image is indicated by r, the coefficient w is indicated by the following Expression (3). In addition, it is assumed that a constant a in Expression (3) is an arbitrarily set value. The "sum of differences between pieces of edge information" d indicated by Expression (1) has a value approaching "0" with increase in the left-right symmetry of the edge image Pie, and the "sum of differences between pieces of edge information" d has a value approaching the "sum of pieces of edge information" s with increase in the left-right asymmetry of the edge image Pie. Therefore, the degree of edge left-right symmetry sym_edg_LR that is the degree of left-right symmetry of the edge image is indicated by the following Expression (4). Namely, the degree of edge left-right symmetry sym_edg_LR has a value whose range is 0 < sym_edg_LR < 1, and has a value approaching "1" with increase in the left-right symmetry of the edge image Pie. In this way, the degree of edge left-right symmetry is calculated. Returning to the flowchart in Fig. 12, in Step S43, the degree-of-up-down-symmetry.calculation unit 53 calculates the degree of edge up-down symmetry that is the degree of up-down symmetry of the edge image, on the basis of the edge image supplied from the edge image generation unit 51. In addition, with respect to the degree of edge up-down symmetry sym_edg_TB, as illustrated in Fig. 15, it is assumed that the center line in the up-down direction of the edge image Pie is a line whose pixel position is H / 2, and attention is focused on a line including pixels in the vertical direction, located at a pixel position j in the left-right direction. In addition, when it is assumed that the pixel position of a pixel located i pixels away on the lower side from a pixel (a pixel whose pixel position is H / 2) on the center line in the up-down direction is represented by "+ i" and the pixel position of a pixel located i pixels away on the upper side from the pixel on the center line in the up-down direction is represented by "- i", the degree of edge up-down symmetry sym_edg_TB is calculated by replacing the value H and the value W with each other in Expressions (1) and (2), in the same way as the degree of edge left-right symmetry sym_edg_LR. In this way, the degree of edge up-down symmetry is calculated. Subsequent to Step S43, the processing returns to Step S31 in the flowchart in Fig. 11, and proceeds to Step S32. Incidentally, when, as the input image, an input image P2 is input in which vegetables as subjects having approximately the same shape and different colors are placed side by side, as illustrated on the left side of Fig. 16, an edge image P2e illustrated on the right side of Fig. 16 is generated in the degree-of-edge-symmetry calculation processing. Since the edge image P2e illustrated in Fig. 16 has high line symmetry with respect to the left-right direction, a great value is obtained as the degree of edge left-right symmetry. However, since the colors of the subjects placed side by side are different from each other in the actual input image P2, it is not necessarily the case that the line symmetry is high with respect to the left-right direction. In this way, in the degree-of-edge-symmetry calculation processing, it is difficult to obtain the line symmetry of the color of the input image. Therefore, in Step S32, the degree-of-color-symmetry calculation unit 42 executes the degree-of-color-symmetry calculation processing, and calculates the degree of color symmetry of the input image, thereby obtaining the line symmetry of the color of the input image. [Degree-of-Color-Symmetry Calculation Processing Performed in Degree-of-Color-Symmetry Calculation Unit] Here, the degree-of-color-symmetry calculation processing performed in Step S31 in the flowchart in Fig. 11 will be described with reference to a flowchart in Fig. 17. In Step S51, the color space conversion unit 61 converts a color space so that individual pixels in the input image represented by an RGB space are represented by an L*a*b*space, for example. The color space conversion unit 61 supplies the input image represented by the L*a*b*space to the degree-of-left-right-symmetry calculation unit 62 and the degree-of-up-down-symmetry calculation unit 63. In Step S52, the degree-of-left-right-symmetry calculation unit 62 calculates the degree of color left-right symmetry that is the degree of left-right symmetry of the input image whose color space is converted by the color space conversion unit 61, the input image being represented by the L*a*b*space. Here, an example of the calculation of the degree of color left-right symmetry will be described. In addition, it is assumed that the input image represented by the L*a*b*space is expressed in the same way as the edge image Pie described with reference to Fig. 14. At this time, in the input image, the sum D of a color difference between a pair of pixels located on opposite sides of the center line in the left-right direction (the pixel position thereof is W / 2), the pixel positions of the pair of pixels being a pixel position (i, j), is indicated by the following Expression (5). In Expression (5), a color difference dE between pixels located at the pixel position (i, j), a difference dL between L*axis components L thereof, a difference da between a*axis components a thereof, and a difference db between b*axis components b thereof are individually indicated by the following Expression (6). dE= dL2+da2+db2 dL=L(i,W/2-j)-L(i,W/2+j) da=a(i,W/2-j)-a(i,W/2+j) db=b(i,W/2-j)-b(i,W/2+j) In addition, a coefficient w in Expression (5) is a weighting coefficient relating to the color difference dE between pixels located at the pixel position (i, j), and the coefficient w is indicated by the following Expression (7). W = Wp • WE In Expression (7), a weighting coefficient wp is a weighting coefficient whose weighting decreases with an increase in the distance of the pixel position (i, j) from the center point of the input image, and the weighting coefficient wp is indicated by the following Expression (8). In addition, it is assumed that a constant P in Expression (8) is an arbitrarily set value. In addition, in Expression (7), a weighting coefficient wE is a weighting coefficient whose weighting is higher in a region in which the color difference dE between pixels located at the attention pixel position (i, j) is larger, and the weighting coefficient wE has such a characteristic as illustrated in Fig. 18. Specifically, when the color difference dE is smaller than a value dEi, the weighting coefficient wE has a value 1.0, and when the color difference dE is greater than a value dE2, the weighting coefficient wE has a value wEM. In addition, when the color difference dE ranges from the value dEi to the value dE2, the weighting coefficient wE also increases in response to the increase of the color difference dE. Namely, the weighting coefficient wE is weighted with respect to the color difference dE so that the color difference dE is more emphasized for a region whose color greatly varies from right to left in such a way as the input image P2 illustrated in Fig. 16. Accordingly, while the "sum of color differences" D indicated by Expression (5) has a value that decreases with increase in the left-right symmetry of the color of the input image, and has a value that increases with increase in the left-right asymmetry of the color of the input image, the "sum of color differences" D is converted as illustrated in Fig. 19, in order to be easy to deal with. Namely, according to Fig. 19, when the sum of color differences D is smaller than the minimum value dEmj.n of the color difference dE between pixels located at the pixel position (i, j), the sum of color differences D' after the conversion has a value "0", and when the sum of color differences D is greater than the maximum value dEmax of the color difference dE between pixels located at the pixel position (i, j), the sum of color differences D' after the conversion has a value "1". In addition, when the sum of color differences D ranges from the dEmin to the dEmax, the sum of color differences D" after the conversion also increases in response to the increase of the sum of color differences D. In addition, the degree of color left-right symmetry sym_col_LR that is the degree of left-right symmetry of the color of the input image is indicated by the following Expression (9). sym_col_LR = 1 -D' (9) Namely, the degree of color left-right symmetry sym_col_LR has a value whose range is o < sym_col_LR < 1, and has a value approaching "1" with increase in the left-right symmetry of the color of the input image. In this way, the degree of color left-right symmetry is calculated. Returning to the flowchart in Fig. 17, in Step S53, the degree-of-up-down-symmetry calculation unit 63 calculates the degree of color up-down symmetry that is the degree of up-down symmetry of the input image whose color space is converted by the color space conversion unit 61, the input image being represented by the L*a*b*space. In addition, with respect to the degree of color up-down symmetry sym_col_TB, in the same way as the edge image Pie illustrated in Fig. 15, it is assumed that the center line in the up-down direction of the input image is a line whose pixel position is H / 2, and attention is focused on a line in the vertical direction, located at the pixel position j in the left-right direction. In addition, when it is assumed that the pixel position of a pixel located i pixels away on the lower side from a pixel (a pixel whose pixel position is H / 2) on the center line in the up-down direction is represented by "+ i" and the pixel position of a pixel located i pixels away on the upper side from the pixel on the center line in the up-down direction is represented by "- i", the degree of edge up-down symmetry sym_edg_TB is calculated by replacing the value H and the value W with each other in Expressions (5) and (6), in the same way as the degree of color left-right symmetry sym_col_LR. In this way, the degree of color up-down symmetry is calculated. Subsequent to Step S53, the processing returns to Step S32 in the flowchart in Fig. 11, and proceeds to Step S33. In Step S33, the degree-of-symmetry determination unit 43 determines the degree of left-right symmetry and the degree of up-down symmetry of the input image on the basis of the degree of edge symmetry supplied from the degree-of-edge-symmetry calculation unit 41 and the degree of color symmetry supplied from the degree-of-color-symmetry calculation unit 42. For example, the degree-of-symmetry determination unit 43 determines, as the degree of left-right symmetry, one of the degree of edge left-right symmetry supplied from the degree-of-edge-symmetry calculation unit 41 and the degree of color left-right symmetry supplied from the degree-of-color-symmetry calculation unit 42, the determined one being smaller than the other. In the same way, the degree-of-symmetry determination unit 43 determines, as the degree of up-down symmetry, one of the degree of edge up-down symmetry supplied from the degree-of-edge-symmetry calculation unit 41 and the degree of color up-down symmetry supplied from the degree-of-color-symmetry calculation unit 42, the determined one being smaller than the other. In addition, the degree-of-symmetry determination unit 43 may also determine, as the degree of left-right symmetry, one of the degree of edge left-right symmetry and the degree of color left-right symmetry, the determined one being greater than the other, and determine, as the degree of up-down symmetry, one of the degree of edge up-down symmetry and the degree of color up-down symmetry, the determined one being greater than the other. The degree-of-symmetry calculation unit 31 supplies, as the degree of symmetry, the degree of left-right symmetry and the degree of up-down symmetry, determined in this way, to the composition classification unit 33, and the processing returns to Step S11 in Fig. 9. After Step S11, in Step S12, the parting line detection unit 32 executes parting line detection processing, and detects a parting line from a variation in the distribution of pixel information in the input image. [Parting Line Detection Processing Performed in Parting Line Detection Unit] Here, the parting line detection processing performed in Step S12 in the flowchart in Fig. 9 will be described with reference to a flowchart in Fig. 20. In Step S71, in the same way as the processing performed in Step S41 in the flowchart in Fig. 12, the edge image generation unit 71 in the parting line detection unit 32 acquires a luminance image from the input image, and generates an edge image that includes an edge value (edge information) obtained by applying an edge extraction filter such as the Sobel filter, the Gabor filter, or the like to the luminance image. In addition, the edge image generation unit 71 may acquire color channel images such as R, G, B and the like, compare edge values, obtained by individually applying the edge extraction filter to the color channel images, with one another between channels with respect to each pixel, and generate an edge image including individual maximum values. Furthermore, the edge image generation unit 71 may also perform the region partitioning of a color, which utilizes a mean shift algorithm'(Mean Shift method) or the like, on the input image, and generate an edge image by assigning an edge value to a pixel on the boundary line of a partitioned region. For example, in this case, an edge value "1" is assigned to a pixel on the boundary line of a region, and an edge value "0" is assigned to a pixel in a region other than the boundary line. For example, when, as illustrated in Fig. 21, a scenery image including the horizon is input as an input image P3, the edge image generation unit 71 generates an edge image P3e that indicates the profile shape of the scene. The edge image P3e generated in this way is supplied to the horizontal parting line detection unit 72 to the oblique parting line detection unit 75. In Step S72, the horizontal parting line detection unit 72 executes horizontal parting line detection.processing, and detects a horizontal parting line partitioning the input image in the horizontal direction (namely, into up and down), on the basis of the edge image supplied from the edge image generation unit 71. [Horizontal Parting Line Detection Processing Performed in Horizontal Parting Line Detection Unit] Here, the horizontal parting line detection processing performed in Step S72 in the flowchart in Fig. 20 will be described with reference to a flowchart in Fig. 22. In Step S81, the horizontal direction integration unit 111 in the horizontal parting line detection unit 72 integrates the edge information with respect to each of lines in the horizontal direction in the edge image supplied from the edge image generation unit 71, and supplies the integration result thereof to the LPF 112. In addition, when integrating the edge information, the horizontal direction integration unit 111 may integrate the edge information after weighting the edge information of each pixel with such a weighting coefficient w as indicated in the above-mentioned Expression (3). Accordingly, an integration value decreases with an increase in the distance of the integration value from the center of the edge image. The integration result obtained here is the integration value of the edge information in the horizontal direction, with respect to a pixel position in the vertical direction in the edge image (input image), and the integration result is plotted by a black diamond shape in a graph illustrated in Fig. 23. Fig. 23 illustrates examples of the integration value in the horizontal direction of the edge information, calculated by the horizontal parting line detection processing, and a value obtained by performing an operation described later on the integration value. In the graph in Fig. 23, a horizontal axis indicates the pixel position in the vertical direction of the edge image (input image). In addition, in Step S82, by performing filtering processing on the integration value of the edge information, supplied from the horizontal direction integration unit 111, the LPF 112 removes noise, and supplies the integration value to the peak value detection unit 113. In Fig. 23, the integration result from which noise is removed is plotted by a white square. In Step S83, the peak value detection unit 113 detects the peak value of the integration value from the integration result from which noise is removed by the LPF 112. Specifically, the peak value detection unit 113 calculates a first differential value (plotted by a white triangle in Fig. 23) of the integration value from which noise is removed, and furthermore, calculates a first differential absolute value (plotted by a cross mark in Fig. 23) that is the absolute value of the first differential value. The peak value detection unit 113 defines, as the peak value of an integration value, an integration value (a point surrounded by a solid line circle in Fig. 23) corresponding to a first differential absolute value (a point surrounded by a dashed line circle in Fig. 23) where the first differential value thereof has a negative value and the first differential absolute value has a local maximum value. Accordingly, in the integration value, a steeply varying peak value is detected. The peak value detection unit 113 supplies to the threshold value processing unit 114 the detected peak value and the pixel position (pixel position 7 in the example of Fig. 23) in the vertical direction of the line in the horizontal direction from which the integration value to be the peak value is obtained. In Step S84, the threshold value processing unit 114 compares the peak value from the peak value detection unit 113 with a predetermined threshold value, and determines whether or not the peak value is greater than the predetermined threshold value. In Step S84, when it is determined that the peak value is greater than the predetermined threshold value, the processing proceeds to Step S85, and the threshold value processing unit 114 defines, as a horizontal parting line, the line in the horizontal direction (line at the pixel position 7 in the vertical direction) from which the integration value to be the peak value is obtained. In addition, the threshold value processing unit 114 outputs, as horizontal parting line information, the pixel position in the vertical direction of the line in the edge image, and the horizontal parting line detection processing is finished. After that, the processing returns to Step S72 in Fig. 20. In this way, when such an input image P3 as illustrated in Fig. 21 is input, the line in the horizontal direction in the horizon portion in the input image P3 is detected as the horizontal parting line as illustrated in Fig. 24. On the other hand, when, in Step S84, it is determined that the peak value is not greater than the predetermined threshold value, the processing in Step S85 is skipped. In this case, the horizontal parting line is not detected, and the horizontal parting line detection processing is finished. After that, the processing returns to Step S72 in Fig. 20. After Step S72, in Step S73, the vertical parting line detection unit 73 executes vertical parting line detection processing, and detects a vertical parting line partitioning the input image in the vertical direction (namely, into right and left), on the basis of the edge image supplied from the edge image generation unit 71. [Vertical Parting Line Detection Processing Performed in Vertical Parting Line Detection Unit] Here, the vertical parting line detection processing performed in Step S73 in the flowchart in Fig. 20 will be described with reference to a flowchart in Fig. 25. In Step S91, the vertical direction integration unit 121 in the vertical parting line detection unit 73 integrates the edge information with respect to each of lines in the vertical direction in the edge image supplied from the edge image generation unit 71, and supplies the integration result thereof to the LPF 122. In addition, when integrating the edge information, the vertical direction integration unit 121 may integrate the edge information after weighting the edge information with such a weighting coefficient w as indicated in the above-mentioned Expression (3). Accordingly, an integration value decreases with an increase in the distance of the integration value from the center of the edge image. The integration result obtained here is the integration value of the edge information in the vertical direction, with respect to a pixel position in the horizontal direction in the edge image (input image), and the integration result is plotted by a black diamond shape in a graph illustrated in Fig. 26. Fig. 26 illustrates examples of the integration value in the vertical direction of the edge information, calculated by the vertical parting line detection processing, and a value obtained by performing an operation described later on the integration value. In the graph in Fig. 26, a horizontal axis indicates the pixel position in the horizontal direction of the edge image (input image). In addition, in Step S92, by performing filtering processing on the integration value of the edge information, supplied from the vertical direction integration unit 121, the LPF 122 removes noise, and supplies the integration value to the peak value detection unit 123. In Fig. 26, the integration result from which noise is removed is plotted by a white square. In Step S93, the peak value detection unit 123 detects the peak value of the integration value from the integration result from which noise is removed by the LPF 122. Specifically, the peak value detection unit 123 calculates a first differential value (plotted by a white triangle in Fig. 26) of the integration value from which noise is removed, and furthermore, calculates a first differential absolute value (plotted by a cross mark in Fig. 26) that is the absolute value of the first differential value. The peak value detection unit 123 defines, as the peak value of an integration value, an integration value corresponding to a first differential absolute value where the first differential value thereof has a negative value and the first differential absolute value has a local maximum value. In Fig. 26, while there is no peak value steeply varying in such a way as in the example in Fig. 23, an integration value to be a peak value is obtained at a pixel position 11 in the horizontal direction. The peak value detection unit 123 supplies to the threshold value processing unit 124 the detected peak value and the pixel position (pixel position 11 in Fig. 26) in the horizontal direction of the line in the vertical direction from which the integration value to be the peak value is obtained. In Step S94, the threshold value processing unit 124 compares the peak value from the peak value detection unit 123 with a predetermined threshold value, and determines whether or not the peak value is greater than the predetermined threshold value. In Step S94, when it is determined that the peak value is greater than the predetermined threshold value, the processing proceeds to Step S95, and the threshold value processing unit 124 defines, as a vertical parting line, the line in the vertical direction from which the integration value to be the peak value is obtained. In addition, the threshold value processing unit 124 outputs, as vertical parting line information, the pixel position in the horizontal direction of the line in the edge image, and the vertical parting line detection processing is finished. After that, the processing returns to Step S73 in Fig. 20. On the other hand, when, in Step S94, it is determined. that the peak value is not greater than the predetermined threshold value, the processing in Step S95 is skipped. For example, when the peak value in Fig. 26 is smaller than the predetermined threshold value, the vertical parting line is not detected, and the vertical parting line detection processing is finished. After that, the processing returns to Step S73 in Fig. 20. After Step S73, in Step S74, the oblique parting line detection unit 74 executes oblique parting line detection processing 1, and detects a first vertical parting line partitioning the input image in an upper right oblique direction, on the basis of the edge image supplied from the edge image generation unit 71. [Oblique Parting Line Detection Processing Performed in Oblique Parting Line Detection Unit] Here, the oblique parting line detection processing 1 performed in Step S74 in the flowchart in Fig. 20 will be described with reference to a flowchart in Fig. 27. Here, when, as illustrated in the top portion in Fig. 28, a scenery image including a mountain the slope of which inclines from upper right to lower left is input as an input image P4, the edge image generation unit 71 generates an edge image P4e indicating the profile shape of the scene, illustrated in the second top portion in Fig. 28, and supplies the input image P4 to the horizontal parting line detection unit 72 to the oblique parting line detection unit 75. In Step S101, the oblique direction integration unit 131 in the oblique parting line detection unit 74 binarizes, into one of "0" and "1", edge information in each of pixels in the edge image supplied from the edge image generation unit 71, on the basis of a predetermined threshold value. For example, when the edge information of the edge image has a value ranging from "0" to "255", the oblique direction integration unit 131 defines, as "0", a pixel value whose value is smaller than a threshold value "127" and defines, as "1", a pixel value whose value is greater than the threshold value "127", with respect to the edge information of the edge image which is a value between "0" and "255". Accordingly, such a binarized edge image P4f as illustrated in the third top portion in Fig. 28 is obtained. In Step S102, the oblique direction integration unit 131 rotates the binarized edge image P4f in a counterclockwise direction so that an upper right oblique diagonal line in the binarized edge image P4f is perpendicular to a horizontal axis in an arbitrarily set coordinate. A rotation angle at this time is calculated on the basis of the aspect ratio of the binarized edge image P4f (input image P4). Accordingly, such a rotated binarized edge image P4r as illustrated in the fourth top portion in Fig. 28 is obtained. Since the binarized edge image P4f that has been binarized is rotated in this way, the number of pixels to be rotation processing targets can be reduced compared with the rotation of the edge image P4e before the binarization. Therefore, an operation cost can be reduced. In Step S103, the oblique direction integration unit 131 integrates the edge information with respect to each of lines in the vertical direction in the set coordinate, in the rotated binarized edge image P4r, in other words, with respect to each of lines in the oblique direction which is parallel to the upper right oblique diagonal line, in the binarized edge image P4f before the rotation, and supplies the integration result thereof to the LPF 132. In addition, when the oblique direction integration unit 131 integrates the edge information in the oblique direction, the number of included pixels varies depending on a line in which the edge information is integrated. Therefore, the oblique direction integration unit 131 normalizes the integration value of the edge information of each line, using the integrated number of pixels. Here, examples of the normalization of the integration value of the edge information with respect to each of lines in the oblique direction will be described with reference to Figs. 29 and 30. Each of Figs. 29 and 30 illustrates a rotated binarized edge image (hereinafter, also simply referred to as edge image) which is rotated so that an upper right oblique diagonal line Dl is perpendicular to an arbitrarily set coordinate (X axis). In addition, as illustrated in each of Figs. 2 9 and 30, it is assumed that the length of the long side of the edge image before the rotation is "a", the length of the short side thereof is "b", and an angle between the long side and the diagonal line Dl is "0". In addition, for example, the edge image is rotated in a counterclockwise direction by 90 degrees - 9 from a state illustrated in the third top portion in Fig. 28, and hence the diagonal line Dl is perpendicular to the X axis. In addition, it is assumed that a coordinate x on the X axis indicates the virtual pixel position of a line in an oblique direction. In addition, in each of Figs. 29 and 30, it is assumed that portions, which are indicated by widths "m" and located at both ends of the edge image projected onto the X axis, are excluded from integration processing targets owing to the low integrated number of pixels thereof. First, as illustrated in Fig. 29, when the line in the oblique direction in which the edge information is integrated is located on the left side of the diagonal line Dl, namely, the range of the coordinate x is m