基于感知器的快速彩色图像无损压缩算法

针对彩色图像像素和颜色分量之间存在的相关性，将神经网络中的感知器技术引入彩色图像的无损压缩算法中，提出了一种新的预测模型。应用感知器的自学习和自适应能力，对预测值进行自适应调整，使算法在运行过程中具有很小的预测残差并具有较小的动态范围。同时应用颜色空间变换来减小颜色分量间的相关性。相对于新的国际标准JPEG—LS，这种预测模型具有较低的计算复杂性。对比实验结果说明，这种算法的性能明显优于传统算法，在压缩比损失很小的前提下，其执行速度高于JPEG—LS。

Fast Lossless Color Image Compressing Method Using Perceptron

A low complexity predictive model is proposed using the correlation of pixels and color components. In the meantime, perception 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 transforms is used and good decorrelation is obtained in our algorithm. Compared to the new standard JPEG-LS, this predictive model reduces its computational complexity. The compared experiments have shown that our algorithm has noticeable better performance than the traditional algorithms. Moreover, its speed is faster than the JPEG-LS with negligible performance sacrifice.