ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술대회 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
저자
박성모, 최병건, 오광일, 김성은, 이주현, 이재진, 강성원
발행일
201711
출처
International SoC Design Conference (ISOCC) 2017, pp.292-293
DOI
https://dx.doi.org/10.1109/ISOCC.2017.8368901
협약과제
17HB1100, 신경모사 인지형 모바일 컴퓨팅 지능형반도체 기술개발, 이주현
초록
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 제안 키워드
Convolution neural network(CNN), Image Compression, Image processing, Object region, compressed images, compression ratio