Comparison of PCA Based and 2DPCA Based Arabic Sign Language Recognition System

الملخص

In order to simplify the communication between the deaf and normal people, several sign language recognition systems have been developed. In this paper, an Arabic Sign Language (ArSR) recognition system was implemented using one-dimensional principal component analysis (PCA), and two-dimensional principal component analysis (2DPCA) respectively. The PCA and 2DPCA are used for image representation and recognition. Compared to PCA, 2DPCA is based on 2D image matrices rather than 1D vectors so that the image matrix does not need to transform into a vector prior to feature extraction. Instead, an image covariance matrix is constructed directly using the original image matrices and its eigenvectors are derived for image feature extraction. The experimental result shows that both PCA and 2DPCA approaches have a good recognition rate and are almost equal, but the 2DPCA approach is more computationally efficient than PCA.