DESC:METHODS AND SYSTEM FOR BRAILLE OBJECT DETECTION ON ARTWORKS
FIELD OF INVENTION
The present invention relates to a system and a method for detecting Braille imprints. More specifically, the present invention relates to a system and a method for detecting Braille imprints on artworks.

BACKGROUND OF INVENTION
Braille is a character system developed for people with visual impairments. Braille includes various combinations of protruded points or dots represented within a 3 by 2 cell, where each combination of protruded dots corresponds to a letter or an alphabet of a language. A latest survey from world health organization (WHO) has stated that around 2.2 billion people are visually impaired globally. Therefore, the visually impaired people rely on the Braille printed on different packaging or artworks to understand the content of the packaging. Manufacturers of various products and services wanting to cater to the visually impaired people along with general public have started to punch dots of a Braille along with printed language on the artworks of the products and services. However, the present manufacturers punch the dots manually on the artworks. Therefore, the dots may not be punched properly and may lack the protrusion, thereby making it hard for the visually impaired people to read information or instructions present on packaging.

Further, manual punching may be prone to having a misplaced Braille dot, wrong spacing between the dots, or punching a Braille dot out of the 3 by 2 cell. A misplaced Braille dot or a wrong spacing between the dots completely changes the meaning of the punched Braille, thereby misguiding a visually impaired person. This makes the Braille on artwork or packaging very crucial, especially in case of medications so that wrong medicine is not taken by a visually impaired person. Therefore, there is a need of a system for automatically detecting Braille imprints on artworks and translating the detected Braille imprints into a language selected by a manufacturer of a product. Such an automation will help the manufacturers to detect any error in the Braille to be printed on the artworks, thereby minimizing manual error and labor, and making the task more efficient.

OBJECT OF INVENTION
The object of the present invention is to provide a system and a method that detects Braille imprints on artworks. More specifically, the object of the present invention is to provide a system a method that detects Braille imprints on artworks automatically and also translates the detected artworks in a language selected by a user so that any error in the artworks can be corrected by the user.

SUMMARY
The present application discloses a system for detecting Braille imprints on artworks. The present application discloses that the system includes a user device monitored by a user, and a Braille detection unit. The Braille detection unit includes an image receiving unit, a colour changing unit, a circle identification unit, an irrelevant circle identification unit, an orientation analysis unit, a rotation unit, a bounding box forming unit, and a translation unit. The image receiving unit is configured to receive an image of an artwork with Braille imprint from the user device. The image includes a plurality of cells of a Braille imprint, where each cell of the Braille imprint comprises a plurality of circles representing a character of a language.

The colour changing unit is configured to change a colour space of the received image of the artwork with Braille imprint to generate a hue image. The colour changing unit changes the colour space of the received artwork image using a hue, saturation, value (HSV) colour space, where the HSV colour space uses a cylindrical polar coordinate system with hue, saturation, and value as coordinates.

The circle identification unit is configured to identify the plurality of circles of the Braille imprint on the hue image. The circle identification unit identifies the plurality of circles using Hough Circle Transform (HCT) based on predetermined threshold values. The circle identification unit uses HCT to produce a plurality of circle candidates by voting in a Hough parameter space and to select a local maxima for each of the plurality of circle candidates to identify the plurality of circles. The circle identification unit is further configured to convert the hue image into a grayscale image if the circle identification unit is not able to identify the plurality circles in the hue image. The circle identification unit first converts the hue image into grayscale image before applying the HCT.

The irrelevant circle identification unit is configured to identify a plurality of irrelevant circles from the identified plurality of circles based on a plurality of predetermined criteria and to filter the identified irrelevant circles from the plurality of circles to obtain a plurality of valid circles. The irrelevant circle identification unit identifies the plurality of irrelevant circles by comparing a median colour of the plurality of circles with a background colour of the artwork, where the irrelevant circle identification unit identifies a circle to be irrelevant if the median colour of the circle is same as the background colour of the artwork.

The orientation analysis unit is configured to determine an orientation of the Braille imprint based on a predefined vertical spacing and a predefined horizontal spacing between the plurality of cells of the Braille imprint. The rotation unit is configured to rotate the Braille imprint if the orientation of the Braille imprint is a vertical orientation to change the vertical orientation into horizontal orientation. The rotation unit rotates the Braille imprint clockwise to 180 degrees if the Braille imprint is at 90 degrees, and rotates the Braille imprint counter-clockwise to 180 degrees if the Braille imprint is at 270 degrees.

The bounding box forming unit is configured to present the plurality of valid circles on an empty image with white background and to find contours of each of the plurality of valid circles to form a bounding box around each cell of the Braille imprint. The bounding box forming unit uses width, height, x-coordinate and y-coordinate for each Braille character to draw a bounding box around each cell representing the Braille character. The plurality of cells with bounding boxes presented on the empty image represent the Braille imprint detected on the Artwork.

The translation unit is configured to translate the detected Braille imprint into a language selected by the user. The user selects the language at the user device and the user device sends the selected language to the translation unit for translating the detected Braille imprint in the selected language.

The present application further discloses a method for detecting Braille imprints on artworks. The method includes receiving, by an image receiving unit, an image of an artwork with Braille imprint. The image comprises a plurality of cells of a Braille imprint, and each cell of the Braille imprint comprises a plurality of circles representing a character of a language. The method further includes changing, by a colour changing unit, a colour space of the received image of the artwork with Braille imprint to generate a hue image. Also, the method includes identifying, by a circle identification unit, the plurality of circles of the Braille imprint on the hue image. The plurality of circles are identified using Hough Circle Transform (HCT) based on predetermined threshold values. The HCT produces a plurality of circle candidates by voting in a Hough parameter space and selecting a local maxima for each of the plurality of circle candidates to identify the plurality of circles.

Further, the method includes identifying, by an irrelevant circle identification unit, a plurality of irrelevant circles from the identified plurality of circles based on a plurality of predetermined criteria and filtering the identified irrelevant circles from the plurality of circles to obtain a plurality of valid circles. The method includes determining, by an orientation analysis unit, an orientation of the Braille imprint based on a predefined vertical spacing and a predefined horizontal spacing between the plurality of cells of the Braille imprint. Also, the method includes rotating, by a rotation unit, the Braille imprint if the orientation of the Braille imprint is a vertical orientation to change the vertical orientation into horizontal orientation.

Furthermore, the method includes presenting, by a bounding box forming unit, the plurality of valid circles on an empty image with white background and finding contours of each of the plurality of valid circles to form a bounding box around each cell of the Braille imprint. The plurality of cells with bounding boxes presented on the empty image represent the Braille imprint detected on the Artwork. The method further includes translating, by a translation unit, the detected Braille imprint into a language selected by a user. The user selects the language at the user device and the user device sends the selected language to the translation unit for translating the detected Braille imprint in the selected language.

BRIEF DESCRIPTION OF DRAWINGS
The novel features and characteristics of the disclosure are set forth in the description. The disclosure itself, however, as well as a preferred mode of use, further objectives, and advantages thereof, will best be understood by reference to the following description of an illustrative embodiment when read in conjunction with the accompanying drawings. One or more embodiments are now described, by way of example only, with reference to the accompanying drawings wherein like reference numerals represent like elements and in which:

FIG. 1 illustrates a system 100 for detecting Braille imprints on artworks, in accordance with an embodiment of the present disclosure.
FIG. 2 illustrates an exemplary scanned image 200 of an artwork with Braille imprint inputted by the user 102, in accordance with an embodiment of the present disclosure.
FIG. 3A illustrates an image of artwork in which a Braille 302 is imprinted on the artwork 304, in accordance with an embodiment of the present disclosure.
FIG. 3B illustrates an image of artwork in which a Braille 306 is imprinted outside the artwork 308, in accordance with an embodiment of the present disclosure.
FIG. 4 illustrates an exemplary Marburg Medium specification 400, in accordance with an embodiment of the present disclosure.
FIG. 5 illustrates an exemplary display 500 of rotation of a Braille imprint, in accordance with an embodiment of the present disclosure.
FIG. 6A illustrates the plurality of valid circles presented on an empty image with white background, in accordance with an embodiment of the present disclosure.
FIG. 6B illustrates a bounding box formed around each cell of the Braille imprint, in accordance with an embodiment of the present disclosure.
FIG. 6C and FIG. 6D illustrate an exemplary scenario in which few circles of a Braille are not marked, in accordance with an embodiment of the present disclosure.
FIG. 7 illustrates an exemplary presentation of detected Braille 702 along with an English translation of the detected Braille 704 based on English language selected by the user 104, in accordance with an embodiment of the present disclosure.
FIG. 8 illustrates a method 800 for detecting Braille imprints on artworks, in accordance with an embodiment of the present disclosure.

The figures depict embodiments of the disclosure for purposes of illustration only. One skilled in the art will readily recognize from the following description that alternative embodiments of the assemblies, structures and methods illustrated herein may be employed without departing from the principles of the disclosure described herein.

DETAILED DESCRIPTION
The best and other modes for carrying out the present invention are presented in terms of the embodiments, herein depicted in drawings provided. The embodiments are described herein for illustrative purposes and are subject to many variations. It is understood that various omissions and substitutions of equivalents are contemplated as circumstances may suggest or render expedient, but are intended to cover the application or implementation without departing from the spirit or scope of the present invention. Further, it is to be understood that the phraseology and terminology employed herein are for the purpose of the description and should not be regarded as limiting. Any heading utilized within this description is for convenience only and has no legal or limiting effect.

The terms “a” and “an” herein do not denote a limitation of quantity, but rather denote the presence of at least one of the referenced items.

The terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process or method that comprises a list of steps does not include only those steps but may include other steps not expressly listed or inherent to such a process or method. Similarly, one or more sub-systems or elements or structures or components preceded by "comprises... a" does not, without more constraints, preclude the existence of other, sub-systems, elements, structures, components, additional sub-systems, additional elements, additional structures or additional components. Appearances of the phrase "in an embodiment", "in another embodiment" and similar language throughout this specification may, but not necessarily do, all refer to the same embodiment.

Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this invention belongs. The system, methods, and examples provided herein are only illustrative and not intended to be limiting.

The system, methods, and examples provided herein are only illustrative and not intended to be limiting.

Embodiments of the present invention will be described below in detail with reference to the accompanying figures.

The present invention focusses on providing a system and a method for detecting Braille imprints on artworks in goods or products produced by diverse industries, such as consumer packaged goods, pharmaceuticals, etc. Sale of any packaged good launched in the market by any industry depends on content about the packaged good given on the packaging. The content present on the packaging is referred to as an artwork related to the packaged good, wherein the artwork includes images, brand name, text, composition, nutritional value table, etc. related to the packaged good. A latest survey from world health organization (WHO) has stated that around 2.2 billion people are visually impaired globally. Therefore, in order to cater to the visually impaired population, many industries have started to imprint Braille along with artworks of packaged goods so that a visually impaired person is able to know the name or content of a packaged good.

However, the present industries imprint Braille on the artworks manually, making the process time consuming and not effective. Also, manual imprints are more error prone as in the manual imprint, a Braille dot or circle may be missed by a person doing the imprint or wrong spacing between Braille dots may be left by the person. This results in mislead information to a visually impaired person, as missed Braille dot and wrong spacing between Braille dots may lead to completely different characters of a language and may provide completely different information about the packaged good to the visually impaired person. Also, such errors lead to a financial loss to industries, as there is no way of detecting these errors before the packaged goods are launched in the market. Further, once wrong Braille is imprinted on artworks of packaged goods in bulk, there is no way of correcting them. The only solution is to redo the entire Braille printing process on new artworks, again leading to money and time loss.

Therefore, the present invention provides a system and a method for detecting Braille imprints on artworks of packaged goods before the packaged goods are packaged and Braille is embossed on the package. The present invention provides a system and a method that detects Braille imprints on artworks automatically and also translates the detected artworks in a language selected by a user so that any error in the artworks can be corrected by the user. The detection of Braille imprints before the packaged goods are packaged eliminates time and money loss as errors in the Braille imprints are detected at an initial stage, thereby allowing a user to correct the errors before the Braille is imprinted on the packaged goods package. Further, the visually impaired people are provided with correct Braille imprints, thereby not being misled.

FIG. 1 illustrates a system 100 for detecting Braille imprints on artworks, in accordance with an embodiment of the present disclosure. The system 100 includes a user device 102 monitored by a user 104, and a Braille detection unit 106. The user device 102 relates to hardware component such as a keyboard, mouse, etc which accepts data from the user 104 and also relates to a hardware component such as a display screen of a desktop, laptop, tablet, etc. which displays data to the user 104. The user device 102 is configured to allow the user 104 to input a scanned image of an artwork related to a packaged good, wherein the scanned image of the artwork also includes a plurality of cells of a Braille imprint for the packaged good. Further, each cell of the Braille imprint comprises a plurality of circles representing a character of a language. The user 104 may be, but not limited to, any employ of an industry monitoring printing of Braille on artworks, a person at a printing unit who may have received printing order of artworks, etc. FIG. 2 illustrates an exemplary scanned image 200 of an artwork with Braille imprint inputted by the user 102, in accordance with an embodiment of the present disclosure. As illustrated in FIG. 2, the user 102 is allowed to choose layers 202 related to the scanned image 200 to make changes in the image 200 before Braille imprint is detected in the image 200.

An image of the artwork with Braille imprint inputted by the user 104 may include, but not limited to, a Braille imprinted on the artwork, or a Braille imprinted outside the artwork. FIG. 3A illustrates an image of artwork in which a Braille 302 is imprinted on the artwork 304, in accordance with an embodiment of the present disclosure. FIG. 3B illustrates an image of artwork in which a Braille 306 is imprinted outside the artwork 308, in accordance with an embodiment of the present disclosure. As illustrated in FIG. 3A and FIG. 3B, the Braille 302 and 306 includes characters of a language, wherein each character is represented by a plurality of circles arranged in a 3 by 2 cell. Further, the artworks 304 and 308 includes information such as name of the medicine, composition and quantity of the medicine, dosage and precaution instruction, storage guidelines, distributer information, bar code, etc. In another embodiment of the present disclosure, an artwork related to a packaged good may be present on one side of a package and a Braille related to the packaged good may be present on the other side of the package.

The user device 102 is further configured to send the image of the artwork with Braille imprint to the Braille detection unit 106. The Braille detection unit 106 is a hardware component which is capable for processing any data or information received by them. In certain embodiments, the Braille detection unit 106 may be part of any regularly devices, such as laptops, desktops, tablets, mobile devices, etc. The Braille detection unit 106 includes an image receiving unit 108, a colour changing unit 110, a circle identification unit 112, an irrelevant circle identification unit 114, an orientation analysis unit 116, a rotation unit 118, a bounding box forming unit 120, and a translation unit 122.

The image receiving unit 108 is configured to receive the image of the artwork with Braille imprint from the user device 102. After receiving the image of the artwork with Braille imprint, the image receiving unit 108 sends the image of the artwork with Braille imprint to the colour changing unit 110.

The colour changing unit 110 is configured to receive the image of the artwork with Braille imprint from the image receiving unit 108 and to change a colour space of the received image of the artwork with Braille imprint to generate a hue image. Changing a colour space of the received image of the artwork with Braille imprint into a hue image is important especially when a Braille is present on an artwork, as in such a scenario a background colour of the artwork may interfere with the colour of Braille circles and may lead to not detecting the Braille imprint properly. Further, a hue colour space handles colours perfectly without a need of deep learning.

In an embodiment of the present disclosure, the colour changing unit 110 uses a hue, saturation, value (HSV) colour space to change the colour of the received image of the artwork with Braille imprint. The HSV colour space uses a cylindrical polar coordinate system with hue, saturation, and value as coordinates. Further, the HSV colour space handles multiple illumination changes, such as global multiplicative changes, global illumination changes, local multiplicative changes, shadow, shading and specular highlights, effectively and efficiently. On the other hand, changing the received image of the artwork with Braille imprint into a grey colour may not be invariant to any of the mentioned illumination changes. In another embodiment, the colour changing unit 110 may use any technique known to change the colour of the received image of the artwork with Braille imprint. After generating the hue image, the colour changing unit 110 sends the hue image to the circle identification unit 112.

The circle identification unit 112 is configured to receive the hue image and to identify the plurality of circles of the Braille imprint on the hue image. The circle identification unit 112 identifies the plurality of circles based on a range of Braille fonts complying with the Marburg Medium specification, as recommended by European and North American standards. FIG. 4 illustrates an exemplary Marburg Medium specification 400, in accordance with an embodiment of the present disclosure. As illustrated in FIG. 4, the Marburg Medium specifications are as shown below:
• The dot or circle diameter is between 1.3-1.6mm;
• a – represents horizontal dot to dot spacing and is 2.5 mm;
• b – represents vertical dot to dot spacing and is 2.5 mm;
• c – represents cell to cell spacing and is 6.0 mm;
• d – represents cell to cell spacing with a single space between the cells and is 12.0 mm;
• e – represents spacing between the first line (Line 1) and the second line (Line 2) and is 10.0 mm.

In an embodiment, the circle identification unit 112 uses a Hough Circle Transform (HCT) to identify the plurality of circles of the Braille imprint on the hue image based on predetermined threshold values. The circle identification unit 112 uses HCT to produce a plurality of circle candidates by voting in a Hough parameter space and to select a local maxima for each of the plurality of circle candidates to identify the plurality of circles. The output of the HCT is an array with a centre x coordinate, a centre y coordinate and a radius value of the circles found. In another embodiment, the circle identification unit 112 may use any other technique known for identifying circles.

Further, the circle identification unit 112 is configured to convert the hue image into a grayscale image if the circle identification unit 112 is not able to identify the plurality of circles in the hue image. The circle identification unit 112 converts the hue image into grayscale image before applying the HCT to identify the plurality of circles of Braille imprint. If the circle identification unit 112 is not able to identify the plurality of circles in the hue image as well as the grayscale image, the circle identification unit 112 continues identifying the plurality of circles in the grayscale image.

The circle identification unit 112 uses the following predetermined threshold values to identify the plurality of circles:
• MIN CENT DIST = 2mm – This represents minimum centre distance between circles to avoid detecting concentric circles. If the minimum centre distance at kept less than 2, then multiple neighbouring circles may be falsely detected in addition to a true one, and if the minimum centre distance is kept more than 2, then some of relevant circles may be missed.
• MAX CIRCLE SIZE RADIUS = 1mm – This represents a maximum circle size used to identify the plurality of circles.
• MIN CIRCLE SIZE RADIUS = 0.6mm – This represents a minimum circle size used to identify the plurality of circles.
• CIRCLE ACCUMULATOR THRESHOLD = 6mm – This represents an accumulator threshold for a plurality of circle centres at a detection stage. The smaller it is, the falser circles may be detected. Circles, corresponding to larger accumulator values, are returned first.
• CANNY HIGHER THRESHOLD = 100 - This represents a threshold value passed to a canny edge detector.

The irrelevant circle identification unit 114 is configured to receive the identified plurality of circles from the circle identification unit 112 and to identify a plurality of irrelevant circles from the identified plurality of circles based on a plurality of predetermined criteria. In an embodiment, a predetermined criteria may include comparing a median colour of each circle from the plurality of circles with a background colour of the artwork. Circles of any Braille are represented by a colour, where median colour is selected by taking the median of the colour of the circles. For example, let us assume that there is a vector V of length N. Then a median of V is given by a middle value of a sorted copy of V and is represented as V(sorted) [(N-1)/2], when N is odd, and an average of two middle values of V(sorted) when N is even. The irrelevant circle identification unit 114 identifies a circle to be irrelevant if the median colour of the circle is same as the background colour of the artwork. Further, there may be a scenario in which a median colour of a circle is not same as a background colour of the artwork, but a median colour of a circle is also not same as a median colour representing Braille circles. In such a case, the irrelevant circle identification unit 114 identifies that circle to be irrelevant.

In an embodiment, a predetermined criteria may include comparing a colour of each circle from the plurality of circles with a threshold value for colour deviation tolerance. For example, a colour deviation allowance for Braille on artwork may be equal to 4; and a colour deviation allowance for Braille outside an artwork may be equal to 4. If some circles from the plurality of circles deviate too much from normal coloured circles, they are identified as irrelevant by the irrelevant circle identification unit 114. The irrelevant circle identification unit 114 is further configured to filter the identified irrelevant circles from the plurality of circles to obtain a plurality of valid circles.

The orientation analysis unit 116 is configured to determine an orientation of the Braille imprint in the hue image based on a predefined vertical spacing and a predefined horizontal spacing between the plurality of cells of the Braille imprint. The orientation of the Braille imprint may include, but not limited to, a vertical orientation or a horizontal orientation. A vertical spacing is defined as a spacing between start of end cell and start of new cell vertically below and a horizontal spacing is defined as a spacing between start of end cell and start of new cell horizontally to the right. If the hue image has vertical orientation (calculated from vertical spacing) and height is greater than width, then the Braille is considered to have a vertical orientation. If the hue image has horizontal orientation and height is shorter that width, then the Braille is considered to have a horizontal orientation.

In an embodiment of the present disclosure, the predefined vertical spacing is 5 (mm) and the predefined horizontal spacing is 3.5 (mm). In another embodiment of the present disclosure, the predefined vertical spacing and the predefined horizontal spacing may include any value based on spacing limits allowed for a Braille imprint.

The rotation unit 118 is configured to rotate the Braille imprint if the orientation of the Braille imprint determined by the orientation analysis unit 116 is a vertical orientation to change the vertical orientation into horizontal orientation. FIG. 5 illustrates an exemplary display 500 of rotation of a Braille imprint, in accordance with an embodiment of the present disclosure. FIG. 5 illustrates a Braille having a vertical orientation 502 being rotated to a horizontal orientation 504. Centre coordinates of the hue image are found to create a two-dimensional rotation matrix. Thereafter, new bounding dimensions of the hue image are computed from rotational components of the two-dimensional rotation matrix and a transformation matrix is found. After getting rotational components, new bounding dimension of the hue image is computed. After adjusting rotational matrix, an actual rotation is done using affine transformation and then returning to the original image. The rotation unit 118 is configured to rotate the Braille imprint clockwise to 180 degrees if the Braille imprint is at 90 degrees, and to rotate the Braille imprint counter-clockwise to 180 degrees if the Braille imprint is at 270 degrees.

The bounding box forming unit 120 is configured to present the plurality of valid circles on an empty image with white background and to find contours of each of the plurality of valid circles to form a bounding box around each cell of the Braille imprint. The plurality of cells with bounding boxes presented on the empty image represent the Braille imprint detected on the Artwork. The bounding box forming unit 120 uses width, height, x-coordinate and y-coordinate for each Braille character to draw a bounding box around each cell representing the Braille character. FIG. 6A illustrates the plurality of valid circles presented on an empty image with white background, in accordance with an embodiment of the present disclosure. FIG. 6B illustrates a bounding box formed around each cell of the Braille imprint, in accordance with an embodiment of the present disclosure. Find contours of each of the plurality of valid circles to form a bounding box around each cell of the Braille imprint is advantageous because it takes into consideration any circles that may have been left unmarked while printing the Braille. FIG. 6C and FIG. 6D illustrate an exemplary scenario in which few circles of a Braille are not marked, in accordance with an embodiment of the present disclosure. FIG. 6C illustrates that circles in column 602 and column 604 are not marked. In such a scenario, the bounding box forming unit 120 considers circles in the second columns 606 and 608 and forms a bounding box around the columns 606 and 608.

The translation unit 122 is configured to translate the detected Braille imprint into a language selected by the user 104. The user 104 selects the language at the user device 102 and the user device 102 sends the selected language to the translation unit for translating the detected Braille imprint in the selected language. FIG. 5 illustrates an input area 506 which allows the user 104 to select a preferred language. FIG. 7 illustrates an exemplary presentation of detected Braille 702 along with an English translation of the detected Braille 704 based on English language selected by the user 104, in accordance with an embodiment of the present disclosure.

FIG. 8 illustrates a method for detecting Braille imprints on artworks, in accordance with an embodiment of the present disclosure. At step 802, the method includes receiving, at an image receiving unit 108, an image of an artwork with Braille imprint. The image includes a plurality of cells of a Braille imprint, and where each cell of the Braille imprint includes a plurality of circles representing a character of a language.

At step 804, the method includes changing, by a colour changing unit 110, a colour space of the received image of the artwork with Braille imprint to generate a hue image. At step 806, the method includes identifying, by a circle identification unit 112, the plurality of circles of the Braille imprint on the hue image. At step 808, the method includes identifying, by an irrelevant circle identification unit 114, a plurality of irrelevant circles from the identified plurality of circles based on a plurality of predetermined criteria and filtering the identified irrelevant circles from the plurality of circles to obtain a plurality of valid circles.

At step 810, the method includes determining, by an orientation analysis unit 116, an orientation of the Braille imprint based on a predefined vertical spacing and a predefined horizontal spacing between the plurality of cells of the Braille imprint. At step 812, the method includes rotating, by a rotation unit 118, the Braille imprint if the orientation of the Braille imprint is a vertical orientation to change the vertical orientation into horizontal orientation.

At step 814, the method includes presenting, by a bounding box forming unit 120, the plurality of valid circles on an empty image with white background and finding contours of each of the plurality of valid circles to form a bounding box around each cell of the Braille imprint. The plurality of cells with bounding boxes presented on the empty image represent the Braille imprint detected on the Artwork. At step 816, the method includes translating, by a translation unit 122, the detected Braille imprint into a language selected by a user 104. The user 104 selects the language at the user device 102 and the user device 102 sends the selected language to the translation unit for translating the detected Braille imprint in the selected language.

The system and method for detecting Braille imprints on artworks disclosed in the present disclosure have numerous advantages. The system and method disclosed detects Braille imprints on artworks automatically and also translates the detected artworks in a language selected by a user so that any error in the artworks can be corrected by the user. The detection of Braille imprints before the packaged goods are packaged eliminates time and money loss as errors in the Braille imprints are detected at an initial stage, thereby allowing a user to correct the errors before the Braille is imprinted on the packaged goods package. Further, the visually impaired people are provided with correct Braille imprints, thereby not being misled. Also, the disclosed system allows a user to select a language for Braille translation from more than 37 languages. Therefore, flexibility of a user to choose a language among multiple languages to translate the detected Braille imprint helps various industries marketing packaged goods in multiple languages in multiple countries to find any error in a Braille imprint.

Further, the system and method disclosed in the present disclosure detects Braille imprints present on artworks as well as Braille imprints present outside the artworks efficiently and effectively. Also, the use of hue colour space handles colours perfectly without a need of deep learning. Furthermore, identification of irrelevant circles based on a plurality of predetermined criteria helps to filter all the irrelevant circles effectively, without filtering actual circles of a Braille imprint. Also, any unmarked circles in a Braille are automatically corrected to detect the Braille correctly.

The embodiments herein and the various features and advantageous details thereof are explained with reference to the non-limiting embodiments in the description. Descriptions of well-known components and processing techniques are omitted so as to not unnecessarily obscure the embodiments herein. The examples used herein are intended merely to facilitate an understanding of ways in which the embodiments herein may be practiced and to further enable those of skill in the art to practice the embodiments herein. Accordingly, the examples should not be construed as limiting the scope of the embodiments herein.

The foregoing description of the specific embodiments will so fully reveal the general nature of the embodiments herein that others can, by applying current knowledge, readily modify and/or adapt for various applications such specific embodiments without departing from the generic concept, and, therefore, such adaptations and modifications should and are intended to be comprehended within the meaning and range of equivalents of the disclosed embodiments.
It is to be understood that the phraseology or terminology employed herein is for the purpose of description and not of limitation. Therefore, while the embodiments herein have been described in terms of preferred embodiments, those skilled in the art will recognize that the embodiments herein can be practiced with modification within the spirit and scope of the embodiments as described herein.

Throughout this specification, the word “comprise”, or variations such as “comprises” or “comprising”, will be understood to imply the inclusion of a stated element, integer or step, or group of elements, integers or steps, but not the exclusion of any other element, integer or step, or group of elements, integers or steps.

The use of the expression “at least” or “at least one” suggests the use of one or more elements or ingredients or quantities, as the use may be in the embodiment of the disclosure to achieve one or more of the desired objects or results.

Any discussion of documents, acts, materials, devices, articles and the like that has been included in this specification is solely for the purpose of providing a context for the disclosure.

It is not to be taken as an admission that any or all of these matters form a part of the prior art base or were common general knowledge in the field relevant to the disclosure as it existed anywhere before the priority date of this application.

The numerical values mentioned for the various physical parameters, dimensions or quantities are only approximations and it is envisaged that the values higher/lower than the numerical values assigned to the parameters, dimensions or quantities fall within the scope of the disclosure, unless there is a statement in the specification specific to the contrary.

While considerable emphasis has been placed herein on the particular features of this disclosure, it will be appreciated that various modifications can be made, and that many changes can be made in the preferred embodiments without departing from the principles of the disclosure. These and other modifications in the nature of the disclosure or the preferred embodiments will be apparent to those skilled in the art from the disclosure herein, whereby it is to be distinctly understood that the foregoing descriptive matter is to be interpreted merely as illustrative of the disclosure and not as a limitation.
,CLAIMS:I/We Claim:
1. A system (100) for detecting Braille imprints on artworks, the system (100) comprising:
an image receiving unit (108) configured to receive an image of an artwork with Braille imprint from a user device (102), wherein the image comprises a plurality of cells of a Braille imprint, and wherein each cell of the Braille imprint comprises a plurality of circles representing a character of a language;
a colour changing unit (110) configured to change a colour space of the received image of the artwork with Braille imprint to generate a hue image;
a circle identification unit (112) configured to identify the plurality of circles of the Braille imprint on the hue image;
an irrelevant circle identification unit (114) configured to identify a plurality of irrelevant circles from the identified plurality of circles based on a plurality of predetermined criteria and to filter the identified irrelevant circles from the plurality of circles to obtain a plurality of valid circles; and
a bounding box forming unit (120) configured to present the plurality of valid circles on an empty image with white background and to find contours of each of the plurality of valid circles to form a bounding box around each cell of the Braille imprint, and wherein the plurality of cells with bounding boxes presented on the empty image represent the Braille imprint detected on the Artwork.

2. The system (100) as claimed in claim 1, wherein the system (100) comprises an orientation analysis unit (116) configured to determine an orientation of the Braille imprint based on a predefined vertical spacing and a predefined horizontal spacing between the plurality of cells of the Braille imprint, wherein the orientation comprises a vertical orientation or a horizontal orientation.

3. The system (100) as claimed in claim 2, wherein the predefined vertical spacing is 5 (mm) and the predefined horizontal spacing is 3.5 (mm).

4. The system (100) as claimed in claim 1, wherein the system (100) comprises a rotation unit (118) configured to rotate the Braille imprint if the orientation of the Braille imprint is a vertical orientation to change the vertical orientation into horizontal orientation.

5. The system (100) as claimed in claim 4, wherein the rotation unit (118) rotates the Braille imprint clockwise to 180 degrees if the Braille imprint is at 90 degrees, and wherein the rotation unit (118) rotates the Braille imprint counter-clockwise to 180 degrees if the Braille imprint is at 270 degrees.

6. The system (100) as claimed in claim 1, wherein the system (100) comprises a translation unit (122) configured to translate the detected Braille imprint into a language selected by a user (104), wherein the user (104) selects the language at the user device (102) and the user device (102) sends the selected language to the translation unit (122) for translating the detected Braille imprint in the selected language.

7. The system (100) as claimed in claim 1, wherein the received image comprises a Braille imprint on an artwork or a Braille imprint outside an artwork.

8. The system (100) as claimed in claim 1, wherein the colour changing unit (110) is configured to change the colour space of the received artwork image using a hue, saturation, value (HSV) colour space, and wherein the HSV colour space uses a cylindrical polar coordinate system with hue, saturation, and value as coordinates.

9. The system (100) as claimed in claim 1, wherein the circle identification unit (112) identifies the plurality of circles using Hough Circle Transform (HCT) based on predetermined threshold values, and wherein the circle identification unit (112) uses HCT to produce a plurality of circle candidates by voting in a Hough parameter space and to select a local maxima for each of the plurality of circle candidates to identify the plurality of circles.

10. The system (100) as claimed in claim 1, wherein the circle identification unit (112) is configured to convert the hue image into a grayscale image if the circle identification unit (112) is not able to identify the plurality circles in the hue image, and wherein the circle identification unit (112) converts the hue image into grayscale image before applying the HCT.

11. The system (100) as claimed in claim 1, wherein the output of the HCT is an array with a centre x coordinate, a centre y coordinate and a radius value of the circles found.

12. The system (100) as claimed in claim 1, wherein the predetermined threshold values used by the circle identification unit comprises:
minimum centre distance between circles to avoid detecting concentric circles = 2 (mm);
maximum circle size used to identify the plurality of circles = 1 (mm);
minimum circle size used to identify the plurality of circles = 0.6 (mm);
accumulator threshold for a plurality of circle centres at a detection stage = 6; and
canny higher threshold = 100.

13. The system (100) as claimed in claim 1, wherein the irrelevant circle identification unit (114) identifies the plurality of irrelevant circles by comparing a median colour of the plurality of circles with a background colour of the artwork, wherein the irrelevant circle identification unit (114) identifies a circle to be irrelevant if the median colour of the circle is same as the background colour of the artwork.

14. The system (100) as claimed in claim 1, wherein the predetermined criteria used by the irrelevant circle identification unit (114) comprises:
comparing a median colour of each circle from the plurality of circles with a background colour of the artwork; and
comparing a colour of each circle from the plurality of circles with a threshold value for colour deviation tolerance, wherein colour deviation allowance for Braille imprint in Artwork is 4, and wherein colour deviation allowance for Braille imprint outside Artwork is 4.

15. The system (100) as claimed in claim 1, wherein the bounding box forming unit (120) uses width, height, x-coordinate and y-coordinate for each Braille character to draw a bounding box around each cell representing the Braille character.

16. A method (800) for detecting Braille imprints on artworks, the method comprising:
receiving, by an image receiving unit (108), an image of an artwork with Braille imprint, wherein the image comprises a plurality of cells of a Braille imprint, and wherein each cell of the Braille imprint comprises a plurality of circles representing a character of a language;
changing, by a colour changing unit (110), a colour space of the received image of the artwork with Braille imprint to generate a hue image;
identifying, by a circle identification unit (112), the plurality of circles of the Braille imprint on the hue image;
identifying, by an irrelevant circle identification unit (114), a plurality of irrelevant circles from the identified plurality of circles based on a plurality of predetermined criteria and filtering the identified irrelevant circles from the plurality of circles to obtain a plurality of valid circles; and
presenting, by a bounding box forming unit (120), the plurality of valid circles on an empty image with white background and finding contours of each of the plurality of valid circles to form a bounding box around each cell of the Braille imprint, and wherein the plurality of cells with bounding boxes presented on the empty image represent the Braille imprint detected on the Artwork.

17. The method as claimed in claim 16, wherein the method comprises determining, by an orientation analysis unit (116), an orientation of the Braille imprint based on a predefined vertical spacing and a predefined horizontal spacing between the plurality of cells of the Braille imprint, wherein the orientation comprises a vertical orientation or a horizontal orientation.

18. The method as claimed in claim 16, wherein the method comprises rotating, by a rotation unit (118), the Braille imprint if the orientation of the Braille imprint is a vertical orientation to change the vertical orientation into horizontal orientation.

19. The method as claimed in claim 16, wherein the method comprises translating, by a translation unit (122), the detected Braille imprint into a language selected by a user (104), wherein the user (104) selects the language at the user device (102) and the user device (102) sends the selected language to the translation unit (122) for translating the detected Braille imprint in the selected language.

20. The method as claimed in claim 16, wherein the plurality of circles are identified using Hough Circle Transform (HCT) based on predetermined threshold values, and wherein the HCT produces a plurality of circle candidates by voting in a Hough parameter space and selecting a local maxima for each of the plurality of circle candidates to identify the plurality of circles.