M-nearest neighbor selection for two-phase test sample representation in face recognition

As a powerful algorithm for face recognition, the proposed Two-Phase Test Sample Representation (TPTSR) increases the classification rate by dividing the recognition task into two steps. The first step intends to find the M most possible candidate training samples from the whole training set to match with the testing input, and the second phase classifies the testing sample to the class with the most representative linear combination by the selected training samples in the first phase. However, the linear representation criterion for selecting the M nearest neighbors in the first phase is too computational demanding, especially when the training set as well as the number of classes is large. Therefore, more straight forward and simplified criterions for the nearest neighbor selection are considered, such as the Euclidean distance and the City-block distance. The experimental results show that the TPTSR method with the Euclidean distance and the City-block distance criterions can achieve almost the same classification performance as the linear representation; they are much more efficient in reducing the computation time.