Handwritten Assamese Character Recognition
Parismita Sarma, Chandan Kumar Chourasia, Manashjyoti Barman · 2019
In various fields of technology, computation techniques are pushing further the limits of human outreach. One such field is the character recognition commonly known as Optical Character Recognition (OCR). This paper is about taking offline handwritten Assamese alphabets as input using modern input devices like camera or scanner and tried to convert it to digital form to recognize the alphabets. Template Matching technique is anticipated for recognizing handwritten characters, including the schemes of Grayscale, Binary, Dilation, Erosion conversion or transformation of image, detection of ROI and comparing with dataset. The efficiency or the accuracy is calculated for every character which is shown in table 1 with a number of testing cases. With this proposed template matching technique we have been able to get accuracy more than 80% for maximum Assamese handwritten alphabets.