A new scheme named personalized image retrieval technique based on visual perception is proposed in this letter, whose motive is to narrow the semantic gap by directly perceiving user's visual information. It uses visual attention model to segment image regions and eye-tracking technique to record fixations. Visual perception is obtained by analyzing the fixations in regions to measure gaze interests. Integrating visual perception into attention model is to detect the Regions Of Interest (ROIs), whose features are extracted and analyzed, then feedback interests to optimize the results and construct user profiles.
This letter presents a novel spatial error concealment algorithm for the H.264 video coding. The error concealment algorithm is based on directional interpolation. Mojette transform is used to estimate the orientation features of the damaged blocks,and the image is interpolated in the appro-priate directions. The proposed method is compared with bilinear interpolation algorithm in the ref-erence implementation of H.264 and all directional interpolation. Experimental results prove that the proposed algorithm has better subjective and objective image reconstruction quality.
