Professional Documents
Culture Documents
Cheques
Aniket Dhanawade, Abhishek Drode, Gifty Johnson, Aadesh Rao and Dr. Savitha Upadhya
Department of Electronics and Telecommunication Engineering, Fr. C.R.I.T.
Authorized licensed use limited to: University of Exeter. Downloaded on June 19,2020 at 13:43:17 UTC from IEEE Xplore. Restrictions apply.
Proceedings of the Fourth International Conference on Computing Methodologies and Communication (ICCMC 2020)
IEEE Xplore Part Number:CFP20K25-ART; ISBN:978-1-7281-4889-2
B. TESSERACT [4]
III. IMPLEMENTATION
Authorized licensed use limited to: University of Exeter. Downloaded on June 19,2020 at 13:43:17 UTC from IEEE Xplore. Restrictions apply.
Proceedings of the Fourth International Conference on Computing Methodologies and Communication (ICCMC 2020)
IEEE Xplore Part Number:CFP20K25-ART; ISBN:978-1-7281-4889-2
Pre-processing is used to generate data that is The linear normalizat ion is performed using the given
suitable for the OCR system to operate precisely. formula:
The OCR system needs clear image with no noise In= (I-Min)*(newMax-newMin)/Max-Min+newMin,
in them. W ithout pre-processing, the system gives Where ‘I’= grayscale image with intensity values
false output. For e.g. the lines in between the dates ranging from (Min, Max) and ‘In’= New image
has to be removed to extract the proper date. This with with intensity values ranging from (newMin,
is achieved by performing binary thresholding. A newMax). [8] b. Binarization [9]
reference threshold is set and the pixel values Image binarization is used to reduce the amount of
below that are made b lack and the once above the image information such as color and background of
threshold are made white. This helps in removing the image, so that output image is black and white.
the bars which are at a higher intensity as This is done by setting a threshold value and
compared to the written date. classifying all the pixels above threshold as white and
below threshold as black. Binarized image is shown in
Pre-processing involves: [6]
Fig. 11.
a. Noise removing or Normalization
Authorized licensed use limited to: University of Exeter. Downloaded on June 19,2020 at 13:43:17 UTC from IEEE Xplore. Restrictions apply.
Proceedings of the Fourth International Conference on Computing Methodologies and Communication (ICCMC 2020)
IEEE Xplore Part Number:CFP20K25-ART; ISBN:978-1-7281-4889-2
Authorized licensed use limited to: University of Exeter. Downloaded on June 19,2020 at 13:43:17 UTC from IEEE Xplore. Restrictions apply.
Proceedings of the Fourth International Conference on Computing Methodologies and Communication (ICCMC 2020)
IEEE Xplore Part Number:CFP20K25-ART; ISBN:978-1-7281-4889-2
[3] https://techterms.com/definition/ocr
[4] https://pypi.org/project/pytesseract/
[5] https://en.wikipedia.org/wiki/OpenCV
[7]https://github.com/alankarmisra/SwiftSignatureView
[8]https://en.wikipedia.org/wiki/Normalization_(image_pro
cessing)
Authorized licensed use limited to: University of Exeter. Downloaded on June 19,2020 at 13:43:17 UTC from IEEE Xplore. Restrictions apply.