상세정보
학술대회
Unsupervised Salient Object Matting
- 발행일
- 201510
- 출처
- International Conference on Advanced Concepts for Intelligent Vision Systems (ACIVS) 2015 (LNCS 9386), pp.752-763
- ISSN
- 0302-9743
- 협약과제
- 15MS4500, (1세부) 실시간 대규모 영상 데이터 이해·예측을 위한 고성능 비주얼 디스커버리 플랫폼 개발, 박경
- 초록
- In this paper, we present a new, easy-to-generate method that is capable of precisely matting salient objects in a large-scale image set in an unsupervised way. Our method extracts only salient object without any user-specified constraints or a manual-thresholding of the saliency-map, which are essentially required in the image matting or saliency-map based segmentation, respectively. In order to provide a more balanced visual saliency as a response to both local features and global contrast, we propose a new, coupled saliency-map based on a linearly combined conspicuity map. Also, we introduce an adaptive tri-map as a refined segmented image of the coupled saliency-map for amore precise object extraction. The proposed method improves the segmentation performance, compared to image matting based on two existing saliency detection measures. Numerical experiments and visual comparisons with large-scale real image set confirm the useful behavior of the proposed method.
- KSP 제안 키워드
- Global contrast, Image Matting, Large scale image, Local feature, Numerical experiments, Object extraction, Saliency detection, image set, salient object, visual saliency