An improved image segmentation algorithm for salient object detection
Yuee Liu, Jinglan Zhang, Dian Tjondronegoro, Shlomo Geva, Zhengrong Li · 2008
Semantic object detection is one of the most important and challenging problems in image analysis. Segmentation is an optimal approach to detect salient objects, but often fails to generate meaningful regions due to over-segmentation. This paper presents an improved semantic segmentation approach which is based on JSEG algorithm and utilizes multiple region merging criteria. The experimental results demonstrate that the proposed algorithm is encouraging and effective in salient object detection.