Scale Invariant Braille Translator Student Yaniv Tocker Final

Scale Invariant Braille Translator Student: Yaniv Tocker Final Project in 'Introduction to Computational & Biological Vision' Course

2 Scale Invariant Braille Translator Background Braille Translator Methods Conclusions Motivation � Optical Character Recognition (OCR): � Automatic translating of letters/digits in images to a form that a computer can manipulate (Strings, ASCII codes)

3 Scale Invariant Braille Translator Background Braille Translator Methods Conclusions Why is this important? � Replacing data entry clerks � Reading car plates � Making electronic copies of books researchable

4 Scale Invariant Braille Translator Background Braille Translator Methods Conclusions Braille OCR � A less investigated field of OCR � Can assist the vision-impaired

5 Scale Invariant Braille Translator Background Braille Translator Methods Conclusions Braille Translator � Goal: being able to translate braille language from an image to English letters � The system is required to be robust to scale changes, since circle can appear in different sizes

6 Scale Invariant Braille Translator Background Braille Translator Methods Conclusions Methods Circle Detection Histogram of Radius Find areas Create Patch Create Dictionary Letter Decision Braille Circles filtered by common radius size & with amount of neighbors Dynamic mask using common radius Original Image Braille meaningful circles mask centers Braille meaningful circles mask Detected Circles Points that Circles are. Braille local filtered maxima Radius by common & Histogram convolution radius result size above a threshold Masks meaningful convolution – creating results patches Circles Mask Braille meaningful circles Dictionary Creation Original Result image First Patch Interpretation Braille patches Dictionary

7 Scale Invariant Braille Translator Background Braille Translator Methods Conclusions GUI � A user friendly GUI was created to easily operate the software

8 Scale Invariant Braille Translator Background Braille Translator Methods Conclusions & Future Work � A scale invariant Braille translator has been proposed � The main key is to find the common radius in the image & build the dictionary according to it � Future addition could be to detect if braille writing is in an image in order to assist the vision impaired

9 Scale Invariant Braille Translator Background Braille Translator Methods Conclusions References 1. OCR: http: //en. wikipedia. org/wiki/Optical_character_recognition 2. Braille OCR http: //en. wikipedia. org/wiki/Optical_braille_recognition 3. Braille OCR example http: //www. ni. com/white-paper/6470/en/ 4. Braille code generator http: //braille. compelo. com/generate/ 5. X. fernanadez et al, “A braille O. C. R for the blind” http: //citeseerx. ist. psu. edu/viewdoc/download? doi=10. 1. 1. 141. 7727&rep=rep 1&type= pdf 6. J. Mennans et al, ”Optical recognition of braillle writing using standard equipment”. http: //bauhaus. ece. curtin. edu. au/~iain/Ph. D%20 BU/A_Phd%20 docs/To%20 read/Ac cessibility%20 info/Research/Braille_Articles/OCR%20 of%20 Braille. pdf 7. O. ben-shahar – lecture notes from ICBV 2014 – - object classification - hough transform

10 Scale Invariant Braille Translator Background Braille Translator Methods Conclusions