Region Based Texture Approximation Technique for Efficient Video Compression

To improve the performance of video compression produced by the previous solution, we propose a region based texture approximation technique. There are situations where the tiny part of the image would vary and transmitting the entire image will not necessary. To overcome such problem, the method splits the video into frames and for each successive frame the method splits the frame into number of regions. Between regions of two successive frames the method computes the feature similarity. Based on the feature similarity the method sends the selective region to the other end, where the method retains the feature of the previous frames for the un received region. This improves the performance of the video compression than the previous method.