Abstract: Now a day’s OCR helps us to recognize text from images but it is not operated with handwritten characters. So we proposed new methodology to recognize handwritten characters. In existing system LoG filter is used to segment the writer’s handwriting image into word regions the SIFT descriptors (SDs) of WRs and the corresponding scales and orientations (SOs) are extracted which is part of SIFT have been utilized to recognize the features.

Keywords: Offline text independent writer identification, SIFT, word segmentation, SIFT descriptor signature, scale and orientation histogram.