Application of the Karhunen-Loeve Procedure for the Characterization of Human Faces
IEEE Transactions on Pattern Analysis and Machine Intelligence
Two-Dimensional PCA: A New Approach to Appearance-Based Face Representation and Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence
Letters: Fast image compression using matrix K-L transform
Neurocomputing
Representing image matrices: eigenimages versus eigenvectors
ISNN'05 Proceedings of the Second international conference on Advances in neural networks - Volume Part II
Hi-index | 0.00 |
A fast image compression method based on 2-Dimensional 2-Direction principal component analysis ((2D)2PCA) to exploit the correlation between rows and columns of image is proposed in this paper. The (2D)2PCA transform is first established from the point view of reconstruction error. And image compression process based on (2D)2PCA is subsequently introduced in detail. Experimental results show that our approach outperforms another fast image compression method based on 2DPCA in that its SNR value is much bigger than the latter over a wide range of compression ratio with slight increase of execution time. Especially at high compression ratio, SNR value of our approach achieves about 0.5--3dB increasing at the condition of the compression ratio of our approach being about twice or even fourth of the latter.