Zernike Moments Based Handwritten Pashto Character Recognition Using Linear Discriminant Analysis

This paper presents an efficient Optical Character Recognition (OCR) system for offline isolated Pashto characters recognition. Developing OCR handwritten character recognition is a challenging task because of the vary both in shape and style most time also among individuals. The identification inscribed letters becomes even palling due to unavailability standard database. For experimental simulation purposes database developed by collecting samples from students university on A4 sized page. These collected are then scanned, stemmed preprocessed form medium that encompasses 14784 images (336 distinguishing each 44 script). Furthermore, Zernike moments considered as feature extractor tool proposed extract features individual character. Linear Discriminant Analysis (LDA) followed based calculated map using moments. Applicability tested validating it with 10-fold cross-validation method overall accuracy 63.71% obtained system.