DESC:An Automated Braille Dots Recognition System and Method Thereof

FIELD OF INVENTION
The present invention generally relates to a field of optical character recognition. More specifically, the present invention relates to an automated system and method for recognition of Braille dots on Braille documents.

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, in order to cater to the visually impaired, significant developments have taken place in production of Braille documents having Braille dots, and in transcription of printed material into Braille since its inception in 1829. However, the conversion of Braille documents to a machine-readable form in order to identify Braille dots on a scanned copy of the Braille documents is still a complicated problem. Most of the known industries or manufacturers identify Braille dots on documents either manually or by scanning, thereby being more prone to errors and human dependent.

Further, most of the known automated systems for identifying Braille dots in scanned Braille documents are not effective and efficient because of special characteristics of the Braille documents and application domain constraints. The Braille documents record Braille in terms of protruded points or dots created by embossing, where the Braille dots may be identified either by detecting the protrusions on one side of the Braille document or depressions on the other side of the Braille documents. However, most of the known automated systems for identifying Braille dots use flatbed scanned documents in which the Braille dots are identified only by detecting the protrusions on the scanned Braille documents. Such systems offer a cost-effective Braille image acquisition solution and are commercially available today. However, such systems do not take into consideration issues of camera- based image acquisition in scanned Braille documents, such as low resolution, irregular lightness, non-uniform illumination. etc.

Therefore, there is a need for an automated system and method for recognition of braille dots on Braille documents. Further, there is a need for an automated system and method for recognition of Braille dots on Braille documents, in which the Braille dots are identified by detecting protrusions on one side of the Braille documents or depressions on the other side of the Braille documents. Furthermore, there is a need for an automated system and method for recognition of Braille dots on Braille documents which corrects issues of camera- based image acquisition in scanned Braille documents, such as low resolution, irregular lightness, non-uniform illumination. etc.

OBJECT OF INVENTION
The object of the present invention is to provide an automated system and method for recognition of Braille dots on Braille documents. The object of the present invention is to recognize or identify Braille dots in Braille documents automatically, thereby being less error-prone, effective and efficient without any human intervention.

SUMMARY
The present application discloses a system for automated recognition of Braille dots on Braille documents. The present application discloses that the system includes a user device monitored by a user, and a Braille dots recognition unit. The Braille dots recognition unit includes an image receiving unit, an image processing unit, a circle identification unit, a bounding box forming unit, and a translation unit. The image receiving unit is configured to receive a scanned image of a Braille document from a user device, wherein the scanned image of the Braille document comprises an image of a plurality of Braille dots embossed on the Braille document.

The image processing unit is configured to check if the Braille dots on the scanned image of the Braille document are properly aligned; and rotate the scanned image of the Braille document by a skew angle in an opposite direction when the Braille dots of the scanned image of the Braille document are not properly aligned. Further, the image processing unit is configured to determine if an orientation of the aligned scanned image of the Braille document is horizontal or vertical, and rotate the aligned scanned image of the Braille document from vertical orientation to horizontal orientation when the orientation of the aligned scanned image of the Braille document is vertical.

The circle identification unit is configured to receive the aligned and oriented scanned image of the Braille document from the image processing unit and to identify a plurality of circles of the Braille dots on the aligned and oriented scanned image of the Braille document. The bounding box forming unit is configured to find contours of each of the identified plurality of circles of the Braille dots to form a bounding box around the identified plurality of circles of the Braille dots; and determine a plurality of valid circles of the Braille dots from the identified plurality of circles of Braille dots based on the bounding box formed around the identified plurality of circles. Further, the bounding box forming unit is configured to draw the plurality of valid circles of the Braille dots on an empty image with white background and find contours of each of the valid circles of the Braille dots to form a bounding box around a cell having a plurality of valid circles representing a character of a language. Also, the bounding box forming unit is configured to apply the formed bounding box around the same cell for which the bounding box is formed on the aligned and oriented image of the Braille document, wherein plurality of cells with bounding boxes on the aligned and oriented image of the Braille document represent the Braille dots recognized on the Braille document.

The present application further discloses a method for automated recognition of Braille dots on Braille documents. The method includes receiving, by an image receiving unit, a scanned image of a Braille document from a user device, wherein the scanned image of the Braille document comprises an image of a plurality of Braille dots embossed on the Braille document. The method further includes checking, by an image processing unit, if the Braille dots on the scanned image of the Braille document are properly aligned. Also, the method includes rotating, by the image processing unit, the scanned image of the Braille document by a skew angle in an opposite direction when the Braille dots of the scanned image of the Braille document are not properly aligned.

Further, the method includes determining, by the image processing unit, if an orientation of the aligned scanned image of the Braille document is horizontal or vertical, and rotating, by the image processing unit, the aligned scanned image of the Braille document from vertical orientation to horizontal orientation when the orientation of the aligned scanned image of the Braille document is vertical. The method includes receiving, by a circle identification unit , the aligned and oriented scanned image of the Braille document from the image processing unit, and identifying, by the circle identification unit, a plurality of circles of the Braille dots on the aligned and oriented scanned image of the Braille document.

Furthermore, the method includes finding, by a bounding box forming unit, contours of each of the identified plurality of circles of the Braille dots to form a bounding box around the identified plurality of circles of the Braille dots. Also, the method includes determining, by the bounding box forming unit, a plurality of valid circles of the Braille dots from the identified plurality of circles of Braille dots based on the bounding box formed around the identified plurality of circles. The method further includes drawing, by the bounding box forming unit, the plurality of valid circles of the Braille dots on an empty image with white background, and finding, by the bounding box forming unit, contours of each of the valid circles of the Braille dots to form a bounding box around a cell having a plurality of valid circles representing a character of a language. The method includes applying, by the bounding box forming unit, the formed bounding box around the same cell for which the bounding box is formed on the aligned and oriented image of the Braille document, wherein plurality of cells with bounding boxes on the aligned and oriented image of the Braille document represent the Braille dots recognized on the Braille document.

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 automated recognition of Braille dots on Braille documents, in accordance with an embodiment of the present disclosure.
FIG. 2 illustrates an exemplary scanned image 200 of Braille document 202 inputted by the user 104, in accordance with an embodiment of the present disclosure.
FIG. 3 illustrates an exemplary Marburg Medium specification 300, in accordance with an embodiment of the present disclosure.
FIG. 4 illustrates a bounding box formed around each of the identified plurality of circles, in accordance with an embodiment of the present disclosure.
FIG. 5 illustrates a plurality of valid circles of the Braille dots 502 drawn on an empty image with white background.
FIG. 6 illustrates a bounding box applied to each cell representing a character of a language on the scanned aligned and oriented image of the Braille document 602, in accordance with an embodiment of the present disclosure.
FIG. 7 illustrates an exemplary presentation of recognized Braille dots 702 along with an English translation of the recognized 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 automated recognition of Braille dots on Braille documents, 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 an automated system and method for recognition of Braille dots on Braille documents related to artworks of goods or products produced by diverse industries, such as consumer packaged goods, pharmaceuticals, etc., or any other documents having Braille dots. 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 or other scannable products having Braille dots (such as pamphlets, books, menus, labels, money cards, etc.) so that a visually impaired person is able to know the name or content of a packaged good or any product having Braille dots. However, the conversion of Braille documents to a machine-readable form in order to identify Braille dots on a scanned copy of the Braille documents is still a complicated problem. Most of the known industries or manufacturers identify Braille dots on documents either manually or by scanning, thereby being more prone to errors and human dependent.

Further, most of the known automated systems for identifying Braille dots in scanned Braille documents are not effective and efficient because of special characteristics of the Braille documents and application domain constraints. Also, most of the known automated systems for identifying Braille dots use flatbed scanned documents in which the Braille dots are identified only by detecting protrusions on one side of the scanned Braille documents. However, such systems do not take into consideration issues of camera- based image acquisition in scanned Braille documents, such as low resolution, irregular lightness, non-uniform illumination. etc.

Therefore, the present invention provides an automated system and method for recognition of braille dots on Braille documents. Further, the present invention provides an automated system and method for recognition of Braille dots on Braille documents, in which the Braille dots are identified by detecting protrusions on one side of the Braille documents or depressions on the other side of the Braille documents. Furthermore, the present invention provides an automated system and method for recognition of Braille dots on Braille documents which corrects issues of camera- based image acquisition in scanned Braille documents, such as low resolution, irregular lightness, non-uniform illumination. etc.

FIG. 1 illustrates a system 100 for automated recognition of Braille dots on Braille documents, 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 dots recognition 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 a Braille document, wherein the Braille document may include, but not limited to, content related to the Braille document and Braille dots embossed on the Braille document. In an embodiment of the present disclosure, the user 104 may use a high quality flat-bed scanner for scanning Braille documents because the flat-bed scanner has a flat surface for scanning documents and can capture all elements on a document without requiring any movement of the document. In another embodiment of the present disclosure, the user 104 may select any scanner for scanning Braille documents based on various criteria and a requirement of the user 104. The various criteria may include, but not limited to, the following:
• Braille document size;
• a resolution value of 600 dpi (dots per inch) for scanning. Lower dpi leads to loss in detail and quality, and lower accuracy;
• Depth estimation. For depth estimation, a 3D (three-dimensional) scanner may be used as depth estimation is not applicable to 2D (two-dimensional) scanners. 3D scanners use multiple lighting to approximate depth to reproduce high quality images where depth may be discerned;
• a scanner with higher colour accuracy representation, thereby producing higher accuracy during comparison; or
• high quality scanners which alleviate noise which may arise due to folding of samples (foils).

The Braille document may include, but not limited to, artworks of goods or products produced by diverse industries, such as consumer packaged goods, pharmaceuticals, etc., or other scannable products having Braille dots (such as pamphlets, books, menus, labels, money cards, etc.). The embossing of Braille dots on a Braille document creates protrusions on one side of the Braille document (usually the side where other content is present) and depressions on the other side of the Braille document (back side of the Braille document). Therefore, a Braille document may also be referred to as a double-sided Braille document. The present invention may consider the protrusions, the depressions or both for recognising the Braille dots on Braille documents.

The user 104 may be, but not limited to, any employ of an industry handling Braille documents, a third-party handling Braille documents, etc. FIG. 2 illustrates an exemplary scanned image 200 of Braille document 202 inputted by the user 104, in accordance with an embodiment of the present disclosure. As illustrated in FIG. 2, the scanned image 200 is an image of the back side of the Braille document 202 having depressions 204 of the Braille dots. FIG. 2 illustrates using back side of the Braille document 202 because the back side of the Braille document 202 does not have any other artwork or content and makes Braille dots easier to read.

The user device 102 is further configured to send the scanned image of the Braille document to the Braille dots recognition unit 106. The Braille dots recognition unit 106 is a hardware component which is capable for processing any data or information received by them. In certain embodiments, the Braille dots recognition unit 106 may be part of any regularly devices, such as laptops, desktops, tablets, mobile devices, etc. The Braille dots recognition unit 106 is configured to recognize a plurality of Braille dots on Braille documents. The Braille dots recognition unit 106 includes an image receiving unit 108, an image processing unit 110, a circle identification unit 112, a bounding box forming unit 114, and a translation unit 116.

The image receiving unit 108 is configured to receive the scanned image of the Braille document from the user device 102. After receiving the scanned image of the Braille document, the image receiving unit 108 sends the scanned image of the Braille document to an image processing unit 110. On receiving the scanned image of the Braille document, the image processing unit 110 checks if the Braille dots on the scanned image of the Braille document are properly aligned or not. In a scenario where the user 104 may place the Braille document incorrectly in the scanner or due to an error in an acquisition machine, the alignment of the Braille dots on the scanned image of the Braille document may be disoriented. Such a disorientation is known as skewing problem.

In an embodiment of the present disclosure, the image processing unit 110 may use a Deskewing technique to correct the alignment of the Braille dots on the scanned image of the Braille document. Deskewing is a technique in which a skew or a misalignment is removed by rotating an image by a same amount as its skew angle but in the opposite direction. This results in a horizontally and vertically aligned image where text runs across a page rather than at an angle. In an embodiment of the present disclosure, the skew angle is obtained by searching for a peak in a histogram of a gradient orientation of the received scanned image of the Braille document, wherein the peak represents a highest value calculated in the histogram of gradient orientation. The skewness of a document is corrected by a rotation at the calculated skew angle. In Braille scanned documents, the skew angle may be, but not limited to, 0o. In another embodiment of the present disclosure, the image processing unit 110 may use any other technique known for correcting the alignment of the Braille dots on the scanned image of the Braille document.

Once the alignment of the Braille dots on the scanned image of the Braille document has been corrected, the image processing unit 110 determines if an orientation of the aligned scanned image of the Braille document is horizontal or vertical. If the orientation of the aligned scanned image of the Braille document is vertical, the image processing unit 110 rotates the aligned scanned image of the Braille document from vertical orientation into horizontal orientation by applying geometric transformation on the aligned scanned image of the Braille document to correct rotation transformation of the aligned scanned image of the Braille document. In order to apply the geometric transformation on the aligned scanned image of the Braille document, the image processing unit 110 first finds dimensions of the aligned scanned image of the Braille document and determines its center coordinates. The centre coordinates are found to calculate a two-dimensional rotation matrix and rotation components of the rotation matrix, where the rotation of a point is based on an angle (90?/ 270? or 0?/ 180?). Rotation of an image for an angle ? is achieved by the transformation matrix of the form:

where: a = scale • cos ?, and
ß = scale • sin ?
Here, a scaled rotation is with adjustable center of rotation so that it may be rotated at any preferred location. After calculating the two-dimensional rotation matrix, the image processing unit 110 computes new bounding dimensions of the aligned scanned image of the Braille document from the rotational components of the two-dimensional rotation matrix and find a transformation matrix. After getting the rotational components, the image processing unit 110 computes new bounding dimension of the aligned scanned image of the Braille document. After adjusting rotational matrix, the image processing unit 110 performs actual rotation of the aligned scanned image of the Braille document using affine transformation and then returning to the original image. The image processing unit 110 is configured to rotate the aligned scanned image of the Braille document clockwise to 180 degrees if the aligned scanned image of the Braille document is at 90 degrees, and to rotate the aligned scanned image of the Braille document counter-clockwise to 180 degrees if the aligned scanned image of the Braille document is at 270 degrees. The image processing unit 110 then sends the aligned and oriented scanned image of the Braille document to the circle identification unit 112.

The circle identification unit 112 is configured to receive the aligned and oriented scanned image of the Braille document from the image processing unit 110 and to identify a plurality of circles of the Braille dots on the aligned and oriented scanned image of the Braille document. 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. 3 illustrates an exemplary Marburg Medium specification 300, in accordance with an embodiment of the present disclosure. As illustrated in FIG. 3, 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 an object detection technique (ODT) for identifying a plurality of circles of the Braille dots on the aligned and oriented scanned image of the Braille document. The output of the ODT 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.

After identifying the plurality of circles of the Braille dots on the aligned and oriented scanned image of the Braille document, the circle identification unit 112 adds the identified plurality of circles of the Braille dots on the aligned and oriented scanned image of the Braille document into a JSON (JavaScript Object Notation) file. The circle identification unit 112 then displays the JSON file to the user 104 on the user device 102. There may be a scenario in which while identifying plurality of circles of the Braille dots, certain dots may be missed, or false positive dots may appear. In such a scenario, when the JSON file is displayed to the user 104, the user 104 may recover the missing dots or may delete the false positive dots and update the JSON file. Once the JSON file has been updated by the user 104, the circle identification unit 112 sends the identified plurality of circles to the bounding box forming unit 114.

The bounding box forming unit 114 is configured to find contours of each of the identified plurality of circles of the Braille dots to form a bounding box around each of the identified plurality of circles of the Braille dots. The bounding box forming unit 114 uses width, height, x-coordinate and y-coordinate for each Braille dot to draw a bounding box around each of the identified plurality of circles. FIG. 4 illustrates a bounding box formed around each of the identified plurality of circles, in accordance with an embodiment of the present disclosure. Forming of bounding box around each of the identified plurality of circles helps in determining valid circles from the identified plurality of circles. For example, there may be a scenario in which the plurality of identified circles may include valid circles corresponding to the Braille dots of the Braille document as well as some false positives present on the Braille document around the Braille dots.

The bounding box forming unit 114 then draws the plurality of valid circles of the Braille dots on an empty image with white background and again finds contours of each of the valid circles of the Braille dots to form a bounding box around each cell having a plurality of valid circles representing a character of a language. The bounding box forming unit 114 then applies the formed bounding box around the same cell for which the bounding box is formed on the scanned aligned and oriented image of the Braille document. FIG. 5 illustrates a plurality of valid circles of the Braille dots 502 drawn on an empty image with white background. FIG. 6 illustrates a bounding box applied to each cell representing a character of a language on the scanned aligned and oriented image of the Braille document 602, in accordance with an embodiment of the present disclosure. The plurality of cells with bounding boxes on the aligned and oriented image of the Braille document represent the Braille dots detected or recognized on the Braille document.

The translation unit 116 is configured to translate the recognized Braille dots 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 116 for translating the detected Braille in the selected language. Referring to FIG. 5, it illustrates an input area 504 which allows the user 104 to select a preferred language. FIG. 7 illustrates an exemplary presentation of recognized Braille dots 702 along with an English translation of the recognized 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 automated recognition of Braille dots on Braille documents, in accordance with an embodiment of the present disclosure. At step 802, the method includes receiving, by an image receiving unit 108, a scanned image of a Braille document from a user device 102, wherein the scanned image of the Braille document comprises an image of a plurality of Braille dots embossed on the Braille document.

At step 804, the method includes checking, by an image processing unit 110, if the Braille dots on the scanned image of the Braille document are properly aligned. The method comprises using, by the image processing unit 110, a Deskewing technique to correct the alignment of the Braille dots on the scanned image of the Braille document.

At step 806, the method includes rotating, by the image processing unit 110, the scanned image of the Braille document by a skew angle in an opposite direction when the Braille dots of the scanned image of the Braille document are not properly aligned. The method comprises obtaining, by the image processing unit 110, the skew angle by searching for a peak in a histogram of a gradient orientation of the received scanned image of the Braille document, wherein the peak represents a highest value calculated in the histogram of gradient orientation.

At step 808, the method includes determining, by the image processing unit 110, if an orientation of the aligned scanned image of the Braille document is horizontal or vertical, and rotating, by the image processing unit 110, the aligned scanned image of the Braille document from vertical orientation to horizontal orientation when the orientation of the aligned scanned image of the Braille document is vertical. The determining, by the image processing unit 110, the orientation of the aligned scanned image of the Braille document is done by applying geometric transformation on the aligned scanned image of the Braille document to correct rotation transformation of the aligned scanned image of the Braille document. Applying the geometric transformation on the aligned scanned image of the Braille document includes:
• finding dimensions of the aligned scanned image of the Braille document and determining its center coordinates to calculate a two-dimensional rotation matrix and rotation components of the rotation matrix;
• computing new bounding dimensions of the aligned scanned image of the Braille document from the rotational components of the two-dimensional rotation matrix and finding a transformation matrix;
• computing new bounding dimension of the aligned scanned image of the Braille document;
• performing actual rotation of the aligned scanned image of the Braille document using affine transformation and return to the original image; and
• rotating the aligned scanned image of the Braille document clockwise to 180 degrees if the aligned scanned image of the Braille document is at 90 degrees, and rotating the aligned scanned image of the Braille document counter-clockwise to 180 degrees if the aligned scanned image of the Braille document is at 270 degrees.

At step 810, the method includes receiving, by a circle identification unit 112, the aligned and oriented scanned image of the Braille document from the image processing unit 110 and identifying, by the circle identification unit 112, a plurality of circles of the Braille dots on the aligned and oriented scanned image of the Braille document. At step 812, the method includes adding, by the circle identification unit 112, the identified plurality of circles of the Braille dots on the aligned and oriented scanned image of the Braille document into a JSON (JavaScript Object Notation) file.

At step 814, the method includes displaying, by the circle identification unit 112, the JSON file to the user 104 and updating, by the circle identification unit 112, the JSON file based on changes made in the JSON file by the user 104.

At step 816, the method includes finding, by a bounding box forming unit 114, contours of each of the identified plurality of circles of the Braille dots to form a bounding box around the identified plurality of circles of the Braille dots. At step 818, the method includes determining, by the bounding box forming unit 114, a plurality of valid circles of the Braille dots from the identified plurality of circles of Braille dots based on the bounding box formed around the identified plurality of circles.

At step 820, drawing, by the bounding box forming unit 114, the plurality of valid circles of the Braille dots on an empty image with white background, and finding, by the bounding box forming unit 114, contours of each of the valid circles of the Braille dots to form a bounding box around each cell having a plurality of valid circles representing a character of a language.

At step 822, the method includes applying, by the bounding box forming unit 114, the formed bounding box around the same cell for which the bounding box is formed on the aligned and oriented image of the Braille document, wherein the plurality of cells with bounding boxes on the aligned and oriented image of the Braille document represent the Braille dots recognized on the Braille document.

At step 824, the method includes translating, by a translation unit 116, the recognized Braille dots into a language selected by the user 104.

The system and method for automated recognition of Braille dots disclosed in the present disclosure have numerous advantages. The system and method disclosed recognises Braille dots on scanned image of Braille documents automatically, thereby being less error-prone, effective and efficient without any human intervention. Further, the system and method disclosed automatically recognises Braille dots on Braille documents, in which the Braille dots are identified by detecting protrusions on one side of the Braille documents or depressions on the other side of the Braille documents. Furthermore, the discloses system and method corrects issues of camera- based image acquisition in scanned Braille documents, such as low resolution, irregular lightness, non-uniform illumination. etc.

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 automated recognition of Braille dots on Braille documents, the system (100) comprising:
an image receiving unit (108) configured to receive a scanned image of a Braille document from a user device (102), wherein the scanned image of the Braille document comprises an image of a plurality of Braille dots embossed on the Braille document;
an image processing unit (110) configured to:
check if the Braille dots on the scanned image of the Braille document are properly aligned;
rotate the scanned image of the Braille document by a skew angle in an opposite direction when the Braille dots of the scanned image of the Braille document are not properly aligned; and
determine if an orientation of the aligned scanned image of the Braille document is horizontal or vertical, and rotate the aligned scanned image of the Braille document from vertical orientation to horizontal orientation when the orientation of the aligned scanned image of the Braille document is vertical; and
a circle identification unit (112) configured to receive the aligned and oriented scanned image of the Braille document from the image processing unit (110) and to identify a plurality of circles of the Braille dots on the aligned and oriented scanned image of the Braille document;
a bounding box forming unit (114) configured to:
find contours of each of the identified plurality of circles of the Braille dots to form a bounding box around the identified plurality of circles of the Braille dots;
determine a plurality of valid circles of the Braille dots from the identified plurality of circles of Braille dots based on the bounding box formed around the identified plurality of circles;
draw the plurality of valid circles of the Braille dots on an empty image with white background, and find contours of each of the valid circles of the Braille dots to form a bounding box around a cell having a plurality of valid circles representing a character of a language; and
apply the formed bounding box around the same cell for which the bounding box is formed on the aligned and oriented image of the Braille document, wherein plurality of cells with bounding boxes on the aligned and oriented image of the Braille document represent the Braille dots recognized on the Braille document.

2. The system (100) as claimed in claim 1, wherein the Braille document comprises content related to the Braille document and a plurality of Braille dots embossed on the Braille document.

3. The system (100) as claimed in claim 1, wherein the image processing unit (110) uses a Deskewing technique to correct the alignment of the Braille dots on the scanned image of the Braille document.

4. The system (100) as claimed in claim 1, wherein the image processing unit (110) obtains the skew angle by searching for a peak in a histogram of a gradient orientation of the received scanned image of the Braille document, wherein the peak represents a highest value calculated in the histogram of gradient orientation.

5. The system (100) as claimed in claim 1, wherein the image processing unit (110) determines the orientation of the aligned scanned image of the Braille document by applying geometric transformation on the aligned scanned image of the Braille document to correct rotation transformation of the aligned scanned image of the Braille document.

6. The system (100) as claimed in claim 5, wherein for applying the geometric transformation on the aligned scanned image of the Braille document, the image processing unit (110) is configured to:
find dimensions of the aligned scanned image of the Braille document and determine its center coordinates to calculate a two-dimensional rotation matrix and rotation components of the rotation matrix;
compute new bounding dimensions of the aligned scanned image of the Braille document from the rotational components of the two-dimensional rotation matrix and find a transformation matrix;
compute new bounding dimension of the aligned scanned image of the Braille document;
perform actual rotation of the aligned scanned image of the Braille document using affine transformation and return to the original image; and
rotate the aligned scanned image of the Braille document clockwise to 180 degrees if the aligned scanned image of the Braille document is at 90 degrees, and to rotate the aligned scanned image of the Braille document counter-clockwise to 180 degrees if the aligned scanned image of the Braille document is at 270 degrees.

7. The system (100) as claimed in claim 1, wherein the circle identification unit (112) identifies the plurality of circles based on a range of Braille fonts complying with the Marburg Medium specification.

8. The system (100) as claimed in claim 1, wherein the circle identification unit (112) uses a Object Detection Technique (ODT) to identify the plurality of circles of the Braille dots on the aligned and oriented scanned image of the Braille document, and wherein an output of the ODT is an array with a centre x coordinate, a centre y coordinate and a radius value of the circles found.

9. The system (100) as claimed in claim 1, wherein the circle identification unit (112) adds the identified plurality of circles of the Braille dots on the aligned and oriented scanned image of the Braille document into a JSON (JavaScript Object Notation) file after identifying the plurality of circles of the Braille dots on the aligned and oriented scanned image of the Braille document.

10. The system (100) as claimed in claim 1, wherein the circle identification unit (112) displays the JSON file to the user (104) and updates the JSON file based on changes made in the JSON file by the user (104).

11. The system (100) as claimed in claim 1, wherein the bounding box forming unit (114) uses width, height, x-coordinate and y-coordinate for each Braille dot to draw a bounding box around each of the identified plurality of circles.

12. The system (100) as claimed in claim 1, wherein the system (100) comprises a translation unit (116) configured to translate the recognized Braille dots into a language selected by the user (104).

13. A method (800) for automated recognition of Braille dots on Braille documents, the method (800) comprising:
receiving, by an image receiving unit (108), a scanned image of a Braille document from a user device (102), wherein the scanned image of the Braille document comprises an image of a plurality of Braille dots embossed on the Braille document;
checking, by an image processing unit (110), if the Braille dots on the scanned image of the Braille document are properly aligned;
rotating, by the image processing unit (110), the scanned image of the Braille document by a skew angle in an opposite direction when the Braille dots of the scanned image of the Braille document are not properly aligned;
determining, by the image processing unit (110), if an orientation of the aligned scanned image of the Braille document is horizontal or vertical, and rotating, by the image processing unit (110), the aligned scanned image of the Braille document from vertical orientation to horizontal orientation when the orientation of the aligned scanned image of the Braille document is vertical;
receiving, by a circle identification unit (112), the aligned and oriented scanned image of the Braille document from the image processing unit (110) and identifying, by the circle identification unit (112), a plurality of circles of the Braille dots on the aligned and oriented scanned image of the Braille document;
finding, by a bounding box forming unit (114), contours of each of the identified plurality of circles of the Braille dots to form a bounding box around the identified plurality of circles of the Braille dots;
determining, by the bounding box forming unit (114), a plurality of valid circles of the Braille dots from the identified plurality of circles of Braille dots based on the bounding box formed around the identified plurality of circles;
drawing, by the bounding box forming unit (114), the plurality of valid circles of the Braille dots on an empty image with white background, and finding, by the bounding box forming unit (114), contours of each of the valid circles of the Braille dots to form a bounding box around a cell having a plurality of valid circles representing a character of a language;
applying, by the bounding box forming unit (114), the formed bounding box around the same cell for which the bounding box is formed on the aligned and oriented image of the Braille document, wherein plurality of cells with bounding boxes on the aligned and oriented image of the Braille document represent the Braille dots recognized on the Braille document.

14. The method (800) as claimed in claim 13, wherein the method comprises using, by the image processing unit (110), a Deskewing technique to correct the alignment of the Braille dots on the scanned image of the Braille document.

15. The method (800) as claimed in claim 13, wherein the method comprises obtaining, by the image processing unit (110), the skew angle by searching for a peak in a histogram of a gradient orientation of the received scanned image of the Braille document, wherein the peak represents a highest value calculated in the histogram of gradient orientation.

16. The method (800) as claimed in claim 13, wherein determining, by the image processing unit (110), the orientation of the aligned scanned image of the Braille document is done by applying geometric transformation on the aligned scanned image of the Braille document to correct rotation transformation of the aligned scanned image of the Braille document.

17. The method (800) as claimed in claim 16, wherein applying, by the image processing unit (110), the geometric transformation on the aligned scanned image of the Braille document comprises:
finding dimensions of the aligned scanned image of the Braille document and determining its center coordinates to calculate a two-dimensional rotation matrix and rotation components of the rotation matrix;
computing new bounding dimensions of the aligned scanned image of the Braille document from the rotational components of the two-dimensional rotation matrix and finding a transformation matrix;
computing new bounding dimension of the aligned scanned image of the Braille document;
performing actual rotation of the aligned scanned image of the Braille document using affine transformation and returning to the original image; and
rotating the aligned scanned image of the Braille document clockwise to 180 degrees if the aligned scanned image of the Braille document is at 90 degrees, and rotating the aligned scanned image of the Braille document counter-clockwise to 180 degrees if the aligned scanned image of the Braille document is at 270 degrees.

18. The method (800) as claimed in claim 13, wherein the method comprises adding, by the circle identification unit (112), the identified plurality of circles of the Braille dots on the aligned and oriented scanned image of the Braille document into a JSON (JavaScript Object Notation) file after identifying the plurality of circles of the Braille dots on the aligned and oriented scanned image of the Braille document.

19. The method (800) as claimed in claim 13, wherein the method comprises displaying, by the circle identification unit (112), the JSON file to the user (104) and updating, by the circle identification unit (112), the JSON file based on changes made in the JSON file by the user (104).

20. The method (800) as claimed in claim 13, wherein the method comprises translating, by a translation unit (116), the recognized Braille dots into a language selected by the user (104).
Dated this 23rd May 2022