Stereoscopic images are widely used to enhance the viewing experience of three-dimensional (3D) imaging and communication\r\nsystem. In this paper, we propose an image feature and disparity dependent quality evaluation metric, which incorporates human\r\nvisible system characteristics. We believe perceived distortions and disparity of any stereoscopic image are strongly dependent\r\non local features, such as edge (i.e., nonplane areas of an image) and nonedge (i.e., plane areas of an image) areas within the\r\nimage. Therefore, a no-reference perceptual quality assessment method is developed for JPEG coded stereoscopic images based\r\non segmented local features of distortions and disparity. Local feature information such as edge and non-edge area based relative\r\ndisparity estimation, as well as the blockiness and the edge distortion within the block of images are evaluated in this method.\r\nSubjective stereo image database is used for evaluation of the metric. The subjective experiment results indicate that our metric\r\nhas sufficient prediction performance.
Loading....