Recognition of Hand Written Devanagari Characters Using LDA

This paper focus on the improvement in performance of recognition system using Principal Component Analysis (PCA) and Linear Discriminate Analysis (LDA). Handwritten character recognition of Devanagari  script is an area of research in the field of pattern recognition. Feature extraction is crucially significant step in recognition system. In handwritten optical character recognition, the size of feature vectors is very high. 

By reducing image size, the dimension of feature vectors can be reduced but this also reduces the pixel information. In proposed system, first raw features are extracted using three different feature extraction methods: chain coding, edge detection using gradient features and direction feature techniques, which are reduced by LDA and characters are classified using SVM classifier.