This course is designed to give postgraduate students an indepth knowledge of pattern recognition methods and their potential applications, in particular in the intelligent pattern recognition field. Lectures cover: Introduction to pattern recognition, definitions and approaches. Statistical Pattern Classification: Decision Theoretic approach: Template Matching (Convolution, Correlation and OCR), Feature Analysis (Stroke Analysis and Geometric Features Analysis), Linear and Nonlinear Decision surface approach. Probabilistic Approach: Bayes Classifier and Gaussian distribution. Syntactic Pattern Classification: Parsing, Pattern Grammar Analysis and Representation, Language analogy grammar and Picture description grammar. Neural Networks Pattern Classification: Neural networks in brief, Activation functions and Topologies. Training strategies (algorithms) and examples of Intelligent Pattern Recognition.