Classification and retrieval of radiology images in H.264/AVC compressed domain. Issue 3 (March 2017)

• Record Type: Journal Article
• Authors: Yamaghani, Mohammadreza; Zargari, Farzad
• Is Part Of: Signal, image and video processing. Volume 11:Issue 3(2017)
• Page Start: 573
• Page End: 580
• Publication Date: 2017-03
• Subjects: Medical images -- Coding -- Classification -- Retrieval -- Compressed domain; Signal processing -- Digital techniques -- Periodicals; Image processing -- Digital techniques -- Periodicals; Digital video -- Periodicals; 621.3822
• DOI: 10.1007/s11760-016-0996-0
• Languages: English
• ISSNs: 1863-1703

Abstract

Abstract The ever-increasing number of produced radiology images in medical centers makes storage, classification and retrieval of these images an important and vital issue in management of medical centers' databases. In this paper, we employ H.264/AVC standard for coding of radiology images and study its performance on storage, classification and retrieval of radiology images. The conducted experiments indicate that coding of radiology images by H.264/AVC standard, on general, reduces the size of coded image to less than half of the coding in PNG format. Moreover, we employ a compressed domain indexing and retrieval method for H.264/AVC coded images, which avoids full decompression of coded image and in turn reduces the indexing and retrieval time. Experimental results indicate that employing this compressed domain feature vector achieves on average 93% accuracy on classification and 85% overall precision in retrieval of radiology images.