Small Sample Problem in Bayes Plug-in Classifier for Image Recognition

applied to discriminate high dimensional data. This classifier is based on similarity measures that involve the inverse of the sample group covariance matrices. These matrices, however, are singular in "small sample size" problems. Therefore, other methods of covariance estimation have been proposed where the sample group covariance estimate is replaced by covariance matrices of various forms. In this paper, a new covariance estimator is proposed and compared with two covariance estimators known as RDA and LOOC. The new estimator does not require an optimisation procedure, but an eigenvector-eigenvalue ordering process to select information from the projected sample group covariance matrices whenever possible and the pooled covariance otherwise. The effectiveness of the method is shown by experimental results carried out on face and facial expression recognition, using different databases for each application