A Noval Approach For Overlapped Character Recogntiton
Gigantic research has been done on optical character recognition (OCR). Numerous works has stated for
English, Chinese and Arabic scripts and Indian languages in . There is no much work done on Overlapped script
recognition. Although different efficient methodologies of Character recognition are proposed, but very few research
implemented on Overlapped script recognition. In this article implemented the latest methods of Overlapped character
recognition. Segmentation of Overlapped characters has an extremely strenuous task due to the large variety of characters
and their shape, their shape and intimacy arrival in the script. Normalization, binarization and thinning are the pre-processing
techniques used for in handwritten character recognition. Finally, we used Support Vector Machine (SVM) for resulting
feature vectors and obtain classification performance in the character recognition scheme in . The implemented
recognition scheme provided 93 percent accuracy on Overlapped English character databases respectively.
Keywords— OCR, Image Processing, Techniques of Overlapped Character Recognition, Chain Code, SVM Classifier.