基于差分和神经网络的同步辐射光源图像压缩方法

针对常见的图像无损压缩方法效果不佳问题,提出了一种基于图像差分和神经网络的同步辐射光源图像无损压缩方法。通过图像差分以减少图像序列内部的线性相关性,训练神经网络模型以学习图像序列内部的非线性相关性,得到预测概率分布,结合算术编码压缩。为加速预测和编码过程,将像素值按位分裂为两部分进行并行处理。基于上海同步辐射光源图像的测试表明,相较于便携式网络图形、JPEG2000和自由无损图像格式等,该方法可将压缩率提升20%以上,像素位分裂可以缩短30%的模型预测和编码时间。

Synchrotron radiation source image compression method based on difference and neural network

For the common image lossless compression methods cannot work well. Thus, a lossless compression method for synchrotron radiation source images based on image difference and neural network was proposed. The image difference method was used to reduce the linear correlations among images. The neural network was trained to learn the nonlinear correlations in the images sequence, and the pixel value was compressed with arithmetic coding using the predicted distribution. To reduce the predicting time and coding time, the pixel value was splitted into two parts for parallel compression. The tests based on the images of Shanghai Synchrotron Radiation Facility show that the proposed method can improve more than 20% in compression ratio compared to PNG(portable network graphics), JPEG2000, FLIF(free lossless image format), and the pixel value split can reduce 30% of the time in predicting and coding.