Citation

Salih, Nbhan D. and Eswaran, Chikkanan and Abid, Abdelouahab (2019) Efficient Retinal Image Compression Based on Modified Huffman Algorithm. International Journal of Engineering Research and Technology, 12 (7). pp. 942-948. ISSN 0974-3154

Text 40j.pdf - Published Version Restricted to Repository staff only Download (544kB)

Abstract

Medical image diagnosis acts an important role recently to protect the life and cure illnesses and therefore practice of medical images is radically improved. Developing technological developments to meet up the memory needs of everyday life looks not to satisfy the necessity of storage as data storage is proportionally improving. Image compression is the crucial solution to satisfy the storage necessities. The prior work presented a numerous compression methods dependent upon Region of Interest (ROI). In this work, an efficient retinal image compression method based on modified Huffman method is presented. The proposed method is designed for improving the storage efficiency and high security. First, the Pre-processing is performed by using Adaptive median filter. To separate out ROI from the preprocessed image, segmentation is performed using Improved Adaptive Fuzzy C-means Clustering. The separated ROI/non-ROI regions are compressed by using Integer Multi Wavelet Transform and Set Partitioning in Hierarchical Trees algorithms respectively. Further, threshold improved zero tree wavelet algorithm is applied on the whole image, and then modified Huffman encoding is performed to obtain compressed image for transmission. The proposed method is tested using a Local database which is collected from local hospitals. The proposed method is a suitable medical image compression with the expected image quality based on the experiments. It’s found that the proposed method yields slightly better CR, PSNR and MSE values compared to existing methods.

Item Type:	Article
Uncontrolled Keywords:	Retinal
Subjects:	R Medicine > RE Ophthalmology
Divisions:	Faculty of Computing and Informatics (FCI)
Depositing User:	Ms Suzilawati Abu Samah
Date Deposited:	27 Apr 2022 00:31
Last Modified:	27 Apr 2022 00:31
URII:	http://shdl.mmu.edu.my/id/eprint/9394

Downloads

Edit (login required)