메뉴 건너뛰기
소속 기관 / 학교 인증
인증하면 논문, 학술자료 등을  무료로 열람할 수 있어요.
한국대학교, 누리자동차, 시립도서관 등 나의 기관을 확인해보세요
(국내 대학 90% 이상 구독 중)
고객센터 ENG
주제분류

피인용 0

검색

    초록·키워드

    We present a novel algorithm for color image quantization based on human color perception properties. The human visual system is very sensitive to the color distortion in the homogeneous regions and distinctive regions, which concentrate great attention of human visual system. So, to reproduce an image using small number of colors, we take into account the spatial distribution of color in an image domain. We construct two kinds of map by analyzing the spatial distributions of color patterns; homogeneity map (H-map) and distinctiveness map (D-map). These maps represent the homogeneity and distinctiveness of each color vector in the spatial domain respectively. Then, we assign weight value to all color vectors by combining these maps to consider two factors at the same time. To extract representative colors, we define a new cost function and use a local K-Means algorithm with weighted color vectors to minimize the cost function. In this stage, we utilize an incremental splitting scheme with a penalty term to determine optimal number of clusters adaptively. The experimental results show that proposed algorithm reproduces an image preserving significant local features while removing unimportant details of an original image from the viewpoint of human. Also, the number of color is determined reasonably.

    최근 본 자료 전체보기

      UCI(KEPA) : I410-ECN-0101-2014-560-003555659