Please use this identifier to cite or link to this item: https://idr.l3.nitk.ac.in/jspui/handle/123456789/15084
Title: Texture Classification based Efficient Image Compression Algorithm for Wireless Capsule Endoscopy
Authors: Sushma B.
Aparna P.
Issue Date: 2019
Citation: 5th International Conference on Computing Engineering and Design, ICCED 2019 , Vol. , , p. -
Abstract: This paper presents a novel method for classification of blocks into smooth and edge blocks in transform domain and a compression scheme for Wireless Capsule Endoscopy (WCE) with block classifier. WCE involves capturing, transmission and processing of gastrointestinal images. Power consumption is a critical issue in WCE, as it uses a button battery driven capsule endoscope to capture and transmit images. The captured image needs to be compressed to save the transmission power and low complexity compressor should be used to avoid more power consumption from the compressor itself. JPEG based compression techniques which consists Discrete Cosine Transform(DCT), quantizer and entropy encoder provides the best compression performance with less complexity compared to other various techniques. Pixel distribution in smooth blocks is uniform and energy is compacted only into low frequency bands in spectral domain. Because high frequency bands are almost having zero energy, only low frequency bands are quantized and entropy coded which saves power in processing high bands. Most of the endoscopic image has smooth region, this method is more suitable to WCE. Proposed algorithm improves compression rate by 9% without sacrificing quality compared to JPEG based compression algorithm. © 2019 IEEE.
URI: https://doi.org/10.1109/ICCED46541.2019.9161103
http://idr.nitk.ac.in/jspui/handle/123456789/15084
Appears in Collections:2. Conference Papers

Files in This Item:
There are no files associated with this item.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.