The technique of lossless image compression plays an important role in image transmission and storage for high quality. At present, both the compression ratio and processing speed should be considered in a real-time multimedia system. A novel lossless compression algorithm is researched. A low complexity predictive model is proposed using the correlation of pixels and color components. In the meantime, perceptron in neural network is used to rectify the prediction values adaptively. It makes the prediction residuals smaller and in a small dynamic scope. Also a color space transform is used and good decorrelation is obtained in our algorithm. The compared experimental results have shown that our algorithm has a noticeably better performance than traditional algorithms. Compared to the new standard JPEG-LS, this predictive model reduces its computational complexity. And its speed is faster than the JPEG-LS with negligible performance sacrifice.
A method of shape encoding and retrieval is proposed in this letter, which uses centripetal code to encode shape and extracts shape's convex for retrieval. For the rotation invariance and translation invariance of the centripetal code and the normalization of convex,the proposed retrieval method is similarity transform resistant, Experimental results confirm this capability.
Huang Xianglin Song Lei Shen Lansun(Signal and Information Processing Lab, Beijing Polytechnic University, Beijing 100022)
