TY - GEN
T1 - A comprehensive study on digital image matting
AU - Yang, Haiyan
AU - Au, Oscar C.
AU - Zeng, Jin
AU - Ji, Mengqi
AU - Yuan, Yuan
AU - Jaiswal, Sunil Prasad
N1 - Publisher Copyright:
© 2014 IEEE.
PY - 2014/9/3
Y1 - 2014/9/3
N2 - Natural image matting refers to the problem of extracting the region of interest such as foreground object from an image based on user inputs like scribbles or trimap. Matting is an ill-posed problem inherently since we need to output three images out of only one input image. After a comprehensive survey and analysis of the existing matting literature, we observe that there are three key components in better estimating the alpha values, that is, the design of matting laplacian matrix, the definition of neighborhood and the choices of feature space. Based on this observation, we introduce a unified framework for digital image matting, which provides the possibility of obtaining a better understanding and direction of further improvement for image matting problem. The experimental results tested on different matting algorithms further prove the feasibility of our proposed framework.
AB - Natural image matting refers to the problem of extracting the region of interest such as foreground object from an image based on user inputs like scribbles or trimap. Matting is an ill-posed problem inherently since we need to output three images out of only one input image. After a comprehensive survey and analysis of the existing matting literature, we observe that there are three key components in better estimating the alpha values, that is, the design of matting laplacian matrix, the definition of neighborhood and the choices of feature space. Based on this observation, we introduce a unified framework for digital image matting, which provides the possibility of obtaining a better understanding and direction of further improvement for image matting problem. The experimental results tested on different matting algorithms further prove the feasibility of our proposed framework.
KW - digital image matting
KW - feature space
KW - local and nonlocal principle
KW - matting laplacian
KW - neighborhood construction
UR - https://www.scopus.com/pages/publications/84929400648
U2 - 10.1109/ChinaSIP.2014.6889249
DO - 10.1109/ChinaSIP.2014.6889249
M3 - 会议稿件
AN - SCOPUS:84929400648
T3 - 2014 IEEE China Summit and International Conference on Signal and Information Processing, IEEE ChinaSIP 2014 - Proceedings
SP - 286
EP - 290
BT - 2014 IEEE China Summit and International Conference on Signal and Information Processing, IEEE ChinaSIP 2014 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2nd IEEE China Summit and International Conference on Signal and Information Processing, IEEE ChinaSIP 2014
Y2 - 9 July 2014 through 13 July 2014
ER -