Multi-view shape recognition based on principal component analysis

Abstract

In this paper, the principal component analysis (PCA) for multi-view shape recognition is proposed. Our algorithm presents the signed enclosed area signature as the shape representation. In our method, the barycenter contour is used for decomposing the shape boundary into multiscale level. At each scale level, the signed enclosed area signatures are obtained. After that, the principal component analysis (PCA) is used as the recognition strategy. This method is independent to starting point of the contour by exploiting the property of the discrete Fourier transform (DFT). In the experimentation, the various number of the sample shapes are used as the training set and the rest are used as the testing set. The experimental results indicate that the recognition accuracy are high enough even one sample shape per class is used as the training set. As the more training sample shapes per class are used, the higher recognition will be. © 2008 IEEE.