摘要：By the rapid change and advancement in technology a need for processing and preserving many texts had been felt. These texts are either in hard copies or in handwritten form. Hand-written numerals, written in various languages and scripts, are an integral part of these texts. Several efforts have been made to recognize numerals and a variety of Optical Character Recognition (OCR) systems have been successfully implemented and marketed. Urdu numerals, as opposed to English numerals, are different due to their style and format of writing. Various methods have been proposed but majority of them only address computer typed numerals in different forms and sizes. Therefore we need to develop new and enhance existing handwritten Urdu numerals recognition systems due to their wide scale use and application in many fields. This research addresses the problem of handwritten offline numerals. A novel approach of Non-negative Matrix Factorization (NMF) for Urdu handwritten character recognition has been proposed in this research.
关键词：Urdu;handwritten;numeral;recognition;optical character recognition;offline;NMF;OCR
