Learned image compression methods generally optimize a rate-distortion loss, trading off improvements in visual distortion for added bitrate. Increasingly, however, compressed imagery is used as an input to deep learning networks various tasks such classification, object detection, and superresolution. We propose recognition-aware learned method, which optimizes loss alongside task-specific joi...

Image compression is an active area of research with a wide range of applications. Being able to represent an image with lesser number of coefficients, without affecting the image quality has been the prime aim of image compression. In this research, a new image compression technique has been proposed, based on Slantlet Transform and the principle of Phase Congruency. The compressed image quali...