Ensembling over-segmentations: From weak evidence to strong segmentation

详细信息    查看全文

• 作者：Dong Huang^a ; ^b ; ^{huangdonghere@gmail.com" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Jian-Huang Lai^b ; ^c ; ^{stsljh@mail.sysu.edu.cn" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Chang-Dong Wang^b ; ^c ; ^{changdongwang@hotmail.com" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Pong C. Yuen^d ; ^{pcyuen@comp.hkbu.edu.hk" class="auth_mail" title="E-mail the corresponding author}Author Vitae
• 关键词：Image segmentation ; Ensemble clustering ; Over-segmentation ; Ensemble segmentation ; Segmentation fusion
• 刊名：Neurocomputing
• 出版年：2016
• 出版时间：26 September 2016
• 年：2016
• 卷：207
• 期：Complete
• 页码：416-427
• 全文大小：9548 K

文摘

Due to the high diversity of image data, image segmentation is still a very challenging problem after decades of development. Each segmentation algorithm has its merits as well as its drawbacks. Instead of segmenting images via conventional techniques, inspired by the idea of the ensemble clustering technique that combines a set of weak clusterers to obtain a strong clusterer, we propose to achieve a consensus segmentation by fusing evidence accumulated from multiple weak segmentations (or over-segmentations). We present a novel image segmentation approach which exploits multiple over-segmentations and achieves segmentation results by hierarchical region merging. The cross-region evidence accumulation (CREA) mechanism is designed for collecting information among over-segmentations. The pixel-pairs across regions are treated as a bag of independent voters and the cumulative votes from multiple over-segmentations are fused to estimate the coherency of adjacent regions. We further integrate the brightness, color, and texture cues for measuring the appearance similarity between regions in an over-segmentation, which, together with the CREA information, are utilized for making the region merging decisions. Experiments are conducted on multiple public datasets, which demonstrate the superiority of our approach in terms of both effectiveness and efficiency when compared to the state-of-the-art.