Recently image coding has been importantand in many field it is necessary. Recently varioussparse algorithms have been developed for imagecompression. This paper presents a dictionary basedblock intra prediction for image compression withconstruction of an adaptive trained dictionary. Theadaptive trained dictionary is prepared using K-SVDalgorithm. K-SVD algorithm update the dictionarybased on the sparse algorithms and given image. Theprediction residuals selected from different image areused for dictionary training. The orthogonal matchingpursuit (OMP) algorithm have employed for selectionof dictionary elements and encoding. The proposedmethod is then integrated into 9 mode H.264 intracoding. Performance of proposed method comparedwith existing methods. Simulation result shows thatproposed scheme has improved efficiency as comparedto existing schemes.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.