1. Visual attention region determination using low-level features
- Author
-
Jin-Jang Leou, Chun-Ying Wu, and Chen Hsuan-Ying
- Subjects
Pixel ,Just-noticeable difference ,Computer science ,business.industry ,media_common.quotation_subject ,Feature extraction ,Pattern recognition ,Image segmentation ,Thresholding ,Luminance ,Human visual system model ,Visual attention ,Contrast (vision) ,Saliency map ,Computer vision ,Artificial intelligence ,business ,Image retrieval ,media_common - Abstract
Visual attention region determination simulates the behavior of the human visual system and determines visual attention regions in an image. In this study, a visual attention region determination approach using low-level features, including luminance, color, and region information, is proposed. First, the contrast map is attained by computing the contrast between each pixel and its “thresholding” neighboring pixels in eight directions, based on the just noticeable difference (JND) model. Then, the block-based edge map and standard deviation representation are used to generate the region mask. The saliency map is obtained by using the contrast map and the region mask. Finally, a visual attention region determination scheme is presented to determine visual attention region(s) in the image. Based on the experimental results obtained in this study, the proposed approach has better performance than two comparison approaches.
- Published
- 2009