Abstract | ||
---|---|---|
This paper presents a novel method for natural image understanding. We improved the effect of saliency detection for the purpose of image segmentation at first. Then Graph cuts are used to find global optimal segmentation of N-dimensional image. After that, we adopt the scheme of supervised learning to classify the scene type of the image. The main advantages of our method are that: Firstly we revised the existed sparse saliency model to better suit for image segmentation, Secondly we propose a new color modeling method during the process of GrabCut segmentation. Finally we extract object-level top down information and low-level image cues together to distinguish the type of images. Experiments show that our proposed scheme can obtain comparable performance to other approaches. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1109/ACPR.2011.6166648 | 2011 FIRST ASIAN CONFERENCE ON PATTERN RECOGNITION (ACPR) |
Keywords | Field | DocType |
Visual Saliency, Image segmentation, GrabCut, Image Understanding | Computer vision,Scale-space segmentation,Pattern recognition,Feature detection (computer vision),Salience (neuroscience),Segmentation,Computer science,Image texture,GrabCut,Segmentation-based object categorization,Image segmentation,Artificial intelligence | Conference |
Volume | Issue | Citations |
null | null | 0 |
PageRank | References | Authors |
0.34 | 0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Qingshan Li | 1 | 0 | 0.34 |
Yue Zhou | 2 | 21 | 4.42 |
Lei Xu | 3 | 13 | 0.97 |