Classification and retrieval of radiology images in H.264/AVC compressed domain

详细信息    查看全文

• 作者：Mohammadreza Yamaghani ; Farzad Zargari
• 关键词：Medical images ; Coding ; Classification ; Retrieval ; Compressed domain
• 刊名：Signal, Image and Video Processing
• 出版年：2017
• 出版时间：March 2017
• 年：2017
• 卷：11
• 期：3
• 页码：573-580
• 全文大小：
• 刊物类别：Engineering
• 刊物主题：Signal,Image and Speech Processing; Image Processing and Computer Vision; Computer Imaging, Vision, Pattern Recognition and Graphics; Multimedia Information Systems;
• 出版者：Springer London
• ISSN：1863-1711
• 卷排序：11

文摘

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.