Research and simulation of generalized statistical pattern recognition

Statistical pattern recognition techniques are exercising dominion over nowadays. But there are many real-world problems the sample is not obey the known Statistical models. And multivariate and small sample problems should be solved in pattern recognition. All of above can't be faultlessly solved by statistical approaches. Generalized statistical pattern recognition method selects proper technique based on the distribution estimation test of samples. It suggests scientific applying the statistical method to pattern recognition and avoiding the distortion and aberration of information because of the statistical method abuse. It also provides a general ways and means of classifier selection which is domain-independent. Firstly, some concerned concepts of special non-statistic were discussed. Then, the process of generalized statistical pattern recognition and non-statistical techniques were introduced. The data experiments of UCI datasets and manual creating dataset based on finite Normal mixture model. The experiment results proved the necessary of generalized statistical pattern recognition.