Pattern Recognition Cai Xuanping, National University of Defense Technology

In terms of its academic connotation, pattern recognition is a subject of data processing and information analysis. In terms of its application characteristics, it belongs to the categories of artificial intelligence and machine learning. The pattern recognition course is a professional basic course for undergraduates in information engineering and related majors. It is also an elective course for many other majors and occupies a very important position in the knowledge structure. It is of great significance for consolidating learned knowledge, carrying out professional course study and future work.

• Chapter 1：Overview (38 minutes and 27 seconds)

• Chapter 2：Feature vectors and feature spaces, random vectors, normal distribution characteristics (39 minutes and 3 seconds)

• Chapter 3：Concepts and similarity measures of cluster analysis (40 minutes and 31 seconds)

• Chapter 4：Similarity measure (2) (41 minutes and 41 seconds)

• Chapter 5：Inter-class distance, criterion function (37 minutes and 0 seconds)

• Chapter 6：Clustering algorithm: simple clustering algorithm, lineage clustering algorithm (42 minutes and 16 seconds)

• Chapter 7：Clustering algorithm: dynamic clustering algorithm-C-means clustering algorithm (32 minutes and 16 seconds)

• Chapter 8：Clustering algorithm: dynamic clustering algorithm-nearest neighbor function algorithm (42 minutes and 46 seconds)

• Chapter 9：Clustering algorithm experiment (6 minutes and 3 seconds)

• Chapter 10：Concept of classification of interface equations in discriminant domain, linear discriminant function (32 minutes and 25 seconds)

• Chapter 11：The identification meaning of discriminant function value, weight space and solution space, fisher linear discriminant (45 minutes and 50 seconds)

• Chapter 12：Discriminant function weight vector algorithm under linearly separable conditions (46 minutes and 43 seconds)

• Chapter 13：Discriminant function weight vector algorithm in general (36 minutes and 43 seconds)

• Chapter 14：nonlinear discriminant function (53 minutes and 42 seconds)

• Chapter 15：nearest neighbor method (39 minutes and 29 seconds)

• Chapter 16：Perceptron algorithm experiment (5 minutes and 10 seconds)

• Chapter 17：Minimum Misjudgment Probability Criterion (38 minutes and 23 seconds)

• Chapter 18：Minimum misjudgment probability and minimum loss criterion judgment of normal distribution (46 minutes and 30 seconds)

• Chapter 19：Minimum loss criterion and minimum maximum loss criterion including rejection judgment (41 minutes and 54 seconds)

• Chapter 20：Neyman-Pearson Judgment, Examples (35 minutes and 47 seconds)

• Chapter 21：Overview, method of moments estimation, maximum likelihood estimation (39 minutes and 2 seconds)

• Chapter 22：Bayesian estimation (36 minutes and 23 seconds)

• Chapter 23：Bayesian learning (44 minutes and 28 seconds)

• Chapter 24：Rough window function estimation method (51 minutes and 51 seconds)

• Chapter 25：Finite term orthogonal function series approximation method (40 minutes and 42 seconds)

• Chapter 26：error rate estimate (30 minutes and 9 seconds)

• Chapter 27：summary (35 minutes and 50 seconds)

• Chapter 28：Experiment 3-4-5 Bayes classifier-kNN classifier-video moving target detection (35 minutes and 11 seconds)

• Chapter 29：Overview, category separability criterion (1) (44 minutes and 2 seconds)

• Chapter 30：Category separability criterion (2) (43 minutes and 27 seconds)

• Chapter 31：Feature extraction based on separability criterion (48 minutes and 28 seconds)

• Chapter 32：Discrete KL transform and feature extraction (32 minutes and 23 seconds)

• Chapter 33：Application of discrete KL transform in feature extraction and selection (32 minutes and 23 seconds)

• Chapter 34：Direct selection method in feature selection (27 minutes and 49 seconds)

• Chapter 35：Comprehensive Experiment-Character Recognition in Images (41 minutes and 21 seconds)