ETRI-Knowledge Sharing Plaform

KOREAN
논문 검색
Type SCI
Year ~ Keyword

Detail

Conference Paper Image Compression based on MR-CNN (Modified Region Convolutional Neural Network)
Cited 1 time in scopus Download 2 time Share share facebook twitter linkedin kakaostory
Authors
Seongmo Park, Byoung Gun Choi, Kwang-Il Oh, S.E. Kim, J.H. Lee, J.J. Lee, Sung Weon Kang
Issue Date
2017-11
Citation
International SoC Design Conference (ISOCC) 2017, pp.292-293
Language
English
Type
Conference Paper
DOI
https://dx.doi.org/10.1109/ISOCC.2017.8368901
Project Code
17HB1100, Brain-Inspired Neuromorphic Perception and Learning Processor, Lee Joo Hyun
Abstract
The proposed algorithm describes compressed image processing based on the Modified Region Convolutional Neural Network (MR-CNN) method. An object extracting unit may classify each of the modified-regions into a background region or an object region on the basis of the degree of pixel changes in the respective set of the modified-regions. There is an efficient compression ratio that can classify an image with each parameter according to the object, text, and background images. The algorithm proposed in the paper improved compression ratio by 10.95% with no degradation compared to the JPEG, and HEVC standards.
KSP Keywords
Convolution neural network(CNN), Image Compression, Image processing, Object region, compressed images, compression ratio