A novel graph-based optimization framework for salient object detection

详细信息    查看全文

• 作者：Jinxia Zhang^a ; ^b ; Author Vitae ; Krista A. Ehinger^c ; ^dAuthor Vitae ; Haikun Wei^a ; ^{hkwei@seu.edu.cn}Author Vitae ; Kanjian Zhang^aAuthor Vitae ; Jingyu Yang^bAuthor Vitae
• 关键词：Optimization framework ; Multiple graphs ; Visual rarity ; Saliency detection
• 刊名：Pattern Recognition
• 出版年：2017
• 出版时间：April 2017
• 年：2017
• 卷：64
• 期：Complete
• 页码：39-50
• 全文大小：1701 K
• 卷排序：64

文摘

A novel graph-based optimization framework for salient object detection is proposed in the paper. Multiple graphs are employed in our optimization framework to better describe a natural scene image. Visual rarity is modeled as a regularization term in our framework to better detect saliency. Experimental results on four datasets with fifteen methods prove the effectiveness of our method.