Combining appearance models and Markov Random Fields for category level object segmentation

Object models based on bag-of-words representations can achieve state-of-the-art performance for image classification and object localization tasks. However, as they consider objects as loose collections of local patches they fail to accurately locate object boundaries and are not able to produce accurate object segmentation. On the other hand, Markov Random Field models used for image segmentation focus on object boundaries but can hardly use the global constraints necessary to deal with object categories whose appearance may vary significantly. In this paper we combine the advantages of both approaches. First, a mechanism based on local regions allows object detection using visual word occurrences and produces a rough image segmentation. Then, a MRF component gives clean boundaries and enforces label consistency, guided by local image cues (color, texture and edge cues) and by long-distance dependencies. Gibbs sampling is used to infer the model. The proposed method successfully seg...

• Type: Conference
• Year: 2008
• Where: CVPR
• Authors: Diane Larlus, Frédéric Jurie
• Keywords: Accurate Object Segmentation, Computer Vision, CVPR 2008, Object Boundaries, Object Categories, Object Localization Tasks, Object Models