International Journal of Computer Applications (0975 – 8887) Volume 2 – No.9, June 2010 38 Printed and Handwritten Character & Number Recognition of Devanagari Script using Gradient Features Anilkumar N. Holambe Department of Information Technology College Of Engineering Osmanabad-413512(M.S.)India Dr.Ravinder.C.Thool Professor and Head Department of Information Technology Shri Guru Gobind Singhji Institute Of Engg & Technology, Vishnupuri, Nanded-431606 (M.S.) India Dr.S.M.Jagade College Of Engineering Osmanabad-413512(M.S.)India ABSTRACT In this paper we are extracting feature of handwritten and ISM printed characters of devanagri script. we are extracting Gradient feature of the devanagari script ,for that we are using two operators i.e. Sobel and Robert operator respectively . Here we are computing gradient in 8,12,16,32 directions and getting different feature vectors respectively. We are using each directional vector separately for classification. Keywords Sobel , Robert, gradient, shirorekha, INTRODUCTION Handwritten recognition is a challenging task in pattern recognition. Researchers for the recognition of Indic Languages and scripts are comparatively less with other languages. A survey on the handwritten recognition has been carried by Plamondon et al [1], Koerich et al [2] and Arica et al [3]. A review on work done for the character recognition before 1990 is reported by Govindan et al [4].The detail survey about the work done for Indian languages script recognition is made by Pal et al [5]. The work on machine printed Devanagari has been made by Bansal et al [6], Pal et al [7] and Chaudhuri et al [8]. The work on handwritten Devanagari numeral is carried by Hanmandlu et al[9] and Bajaj et al[10]. Some models that have been implemented for the Hand written Character Recognition system are described in [11,12,13,14 ].A character recognition system consist of three main components, they are preprocessing, feature extraction and classification. 1. DEVANAGARI SCRIPT AND DATA COLLECTION Devanagari is the script for Hindi, Sanskrit, Marathi, and Nepali languages. Devanagari script is a logical composition of its constituent symbols in two dimensions .It is an alphabetic script. Devanagari has 11 vowels and 33 simple consonants. Besides the consonants and the vowels, other constituent symbols in Devanagari are set of vowel modifiers called matra (placed to the left, right, above, or at the bottom of a character or conjunct), pure-consonant (also called half-letters) which when combined with other consonants yield conjuncts. A horizontal line called shirorekha (a header line) runs through the entire span of work[15]. Some illustrations are given in Figure 1. Figure.1.Characters and matra for devnagari Script. In the present work we have developed printed and handwritten database. For printed we have used different ISM office fonts. For handwritten we have collect data from people of different age groups and from different profession. We have visited primary school, secondary school, High school, Government offices, Adult Education Night school for collecting data. This data were scanned at 300 dpi using a HP flatbed scanner and stored as gray- level images. A few samples from this database are shown in Figure 2 .and Figure 3. The preprocessing steps performed in this work are steps for rectification of distorted images, improving the quality of images for ensuring better quality edges in the subsequent edge determination step and size normalization. Here we are using both database for our results. Figure.2. Data sheet for Devanagari Character