Edge based enhancement of retinal images using an efficient JPEG-compressed domain technique

Article Type

Research Article

Publication Title

Journal of Intelligent and Fuzzy Systems


With substantial usage of Imaging Technology in the medical field for the diagnosis and treatment of illnesses, a huge volume of medical images are being generated which provide a bigger challenge in terms of storage, transmission and processing. The high resolution medical images thus generated occupy large storage space, and hence they are subjected to compression to make them storage and transmission efficient. Though compression overcomes the issues of storage and transmission to some extent, but the problem of processing compressed images still remains as a challenge. This is because; the usual way of processing the compressed medical images is through the operations of decompression and recompression, which consume lots of computing resources. Therefore, it would be novel, if the compressed medical images are processed and analysed directly in the compressed formats without involving the expensive operations like decompression and recompression. In this direction, the current research paper demonstrates a novel technique of edge based enhancement of retinal images, which is a very critical operation from disease diagnosis perspective, directly in the JPEG compressed domain. The developed algorithm is validated with publicly available retinal datasets of DRIVE and DIARETDB1, and the performance reported is compared with the state-of-the-art techniques in the uncompressed (spatial) domain in terms of both quality of enhancement and computation time.

First Page


Last Page




Publication Date