TY - JOUR ID - 479 TI - Holistic Farsi handwritten word recognition using gradient features JO - Journal of AI and Data Mining JA - JADM LA - en SN - 2322-5211 AU - Imani, Z. AU - Ahmadyfard, Z. AU - Zohrevand, A. AD - Electrical Engineering Department, University of Shahrood, Shahrood, Iran. AD - Electrical Engineering Department, University of Shahrood, Shahrood, Iran AD - Computer Engineering & Information Technology Department, University of Shahrood, Shahrood, Iran. Y1 - 2016 PY - 2016 VL - 4 IS - 1 SP - 19 EP - 25 KW - Handwritten word recognition KW - Directional gradient feature KW - Hidden Markov Model KW - Self-organizing feature map KW - FARSA database DO - 10.5829/idosi.JAIDM.2016.04.01.03 N2 - In this paper we address the issue of recognizing Farsi handwritten words. Two types of gradient features are extracted from a sliding vertical stripe which sweeps across a word image. These are directional and intensity gradient features. The feature vector extracted from each stripe is then coded using the Self Organizing Map (SOM). In this method each word is modeled using the discrete Hidden Markov Model (HMM). To evaluate the performance of the proposed method, FARSA dataset has been used. The experimental results show that the proposed system, applying directional gradient features, has achieved the recognition rate of 69.07% and outperformed all other existing methods. UR - https://jad.shahroodut.ac.ir/article_479.html L1 - https://jad.shahroodut.ac.ir/article_479_e7162affb57e373e86915d6960bf1f90.pdf ER -