TY - JOUR
T1 - OCR based pixel fusion
AU - Al-Hmouz, Rami
PY - 2012
Y1 - 2012
N2 - Character recognition is the process that allows the automatic identification of character images, which is generally referred as Optical Character Recognition (OCR). The characters are either handwritten or typed. This study proposed a novel OCR approach based on the likelihood functions of pixels, which were obtained by averaging a trained set of character images. A Bayesian fusion process for all pixel probabilities decides the recognition of characters. Further tests using Support Vector Machine (SVM) classifier were carried out on characters with the same shape. This method was used to test noisy images and achieved an accuracy of 97.95%, thus, outperforming other OCR methods.
AB - Character recognition is the process that allows the automatic identification of character images, which is generally referred as Optical Character Recognition (OCR). The characters are either handwritten or typed. This study proposed a novel OCR approach based on the likelihood functions of pixels, which were obtained by averaging a trained set of character images. A Bayesian fusion process for all pixel probabilities decides the recognition of characters. Further tests using Support Vector Machine (SVM) classifier were carried out on characters with the same shape. This method was used to test noisy images and achieved an accuracy of 97.95%, thus, outperforming other OCR methods.
KW - Bayes theorem
KW - Fusion
KW - Optical character recognition
KW - Pixel likelihood function
UR - http://www.scopus.com/inward/record.url?scp=84871868881&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84871868881&partnerID=8YFLogxK
U2 - 10.3923/jas.2012.2319.2325
DO - 10.3923/jas.2012.2319.2325
M3 - Article
AN - SCOPUS:84871868881
SN - 1812-5654
VL - 12
SP - 2319
EP - 2325
JO - Journal of Applied Sciences
JF - Journal of Applied Sciences
IS - 22
ER -