Image Coding For Region Of Visual Saliency

With the development of the times, video data and image data exist everywhere.Huge amounts of data have attracted people’s attention. The big data brings a lot ofinformation and promotes the development rapidly. However, it also causes a lot ofproblems, such as storage problem and bandwidth problem. Therefore, image codingis still one of the main research topics. Common image coding method is aimed at thewhole picture for compressing each object to the best. But in fact, the human eyesfocus on a partial region of the image rather than all of them. That is called visualsaliency. In this paper, we use the principle of visual saliency to make sure the qualityof interest region at the cost of reduction of the quality in non-interest region. Weproposed three kinds of implement method.First, the coding method based on quantization which controlling by depth.Directly use of depth map to be visual saliency map. That is to say, make the regionclosed to the image device as the region of interest and the other region as the regionof non-interest. And distribute more bits to the region of interest through adjusting thequantization parameter values in the HEVC. The other region is distributed less.Second, the coding method based on the depth of field reconstruction. Themethod used HC method and depth information to get visual saliency map. That isregion of interest map. And then reconstruct the region of field by the saliency mapand depth map.Third, the coding method based on the principle of rate distortion optimizationvisual significant. Count the QP, rate bits and distortion in each block by encodingHEVC. Then use the saliency map as the weight to calculate the best QP by the ratedistortion optimization theory. At last use the QP to encode the image.Through a lot of experiments, contrast with the original method in the latestcoding standard HEVC. We proved our method’s advantages by using two kinds ofevaluation method the subjective and the objective one.