JPR_V2_N1_RP2 M.S. Patel S.C. Linga Reddy Journal on Pattern Recognition 2350-112X 2 1 10 15 Handwritten Kannada Word Recognition, Subspace Approach, Generalized Regression Neural Network, Probabilistic Neural Network, Classification The challenges in OCR system are many in the area of Handwritten Character and Word Recognition. From its very nature, Handwritten Character Word is a mixture of cursive and non-cursive segments. This leads to the problem of Recognition being significantly difficult. In this paper, the authors propose an intelligent system for recognition of handwritten Kannada words for recognition of the names of Districts and Taluks written on boards, land marks, etc. The proposed system applies an idea of subspace approach with popular Neural Network Architectures such as Generalized Regression Neural Network (GRNN) and Probabilistic Neural Network (PNN) for classification. This method is experimented on handwritten words comprising 189 (District & Taluk names of Karnataka State) classes. March - May 2015 Copyright © 2015 i-manager publications. All rights reserved. i-manager Publications http://www.imanagerpublications.com/Article.aspx?ArticleId=3371