ETRI-Knowledge Sharing Plaform

KOREAN
논문 검색
Type SCI
Year ~ Keyword

Detail

Conference Paper UnAMT: Unsupervised Adaptive Matting Tool for Large-scale Object Collections
Cited 0 time in scopus Download 9 time Share share facebook twitter linkedin kakaostory
Authors
Jaehwan Kim, JongYoul Park, Kyoung Park
Issue Date
2015-08
Citation
ACM SIGGRAPH Asia 2015, pp.1-1
Language
English
Type
Conference Paper
DOI
https://dx.doi.org/10.1145/2787626.2792644
Project Code
15MS4500, Development of High Performance Visual BigData Discovery Platform, Park Kyoung
Abstract
Unsupervised matting, whose goal is to extract interesting fore- ground components from arbitrary and natural background regions without any additional information of the contents of the corre- sponding scenes, plays an important role in many computer vision and graphics applications. Especially, the precisely extracted object images from the matting process can be useful for automatic gener- Ation of large-scale annotated training sets with more accuracy, as well as for improving the performance of a variety of applications including content-based image retrieval. However, unsupervised matting problem is intrinsically ill-posed so that it is hard to gen- erate a perfect segmented object matte from a given image with- out any prior knowledge. This additional information is usually fed by means of a trimap which is a rough pre-segmented image consisting of three subregions of foreground, background and un- known. When such matting process is applied to object collections in a large-scale image set, the requirement for manually specifying every trimap for each of independent input images can be a serious drawback definitely. Recently, automatic detection of salient object regions in images has been widely researched in computer vision tasks including image segmentation, object recognition and so on. Although there are many different types of proposal measures in methodology under the common perceptual assumption of a salient region standing out its surrounding neighbors and capturing the at- Tention of a human observer, most final saliency maps having lots of noises are not sufficient to take advantage of the consequent com- putational processes of highly accurate low-level representation of images.
KSP Keywords
Automatic Detection, Computer Vision(CV), Content based image retrieval, Highly accurate, Ill-posed, Large scale image, Large-scale object, Natural background, Object Recognition, Saliency Map, Unsupervised matting