This paper summarized some major methods in image progressing and existent problems. Also we analyzed and summarized the support vector machine pattern recognition which is described as a new direction in pattern recognition in recent years.

It is important to extract pattern's feaure and recognize them by proper model in pattern classification. In this paper, we propose the modified LDA to compress the extracted feature, and design the classifier with Precision Constrained Gaussian Model .A series of experiments are offered and the experimental result shows that our PCGM can achieve a much better generalization and MLDA has a better performance than LDA in classification. Key Word: Precision Constrained Gaussian Model (PCGM ) LDA online Handwritten Recognition.