点击次数：

论文类型：期刊论文

第一作者：Wang,Xinggang

通讯作者：Feng,Bin

合写作者：Latecki,Jan,Longin,Liu,Wenyu,Bai,Xiang

发表刊物：Pattern Recognition

DOI码：10.1016/j.patcog.2013.12.008

发表时间：2014-01-03

影响因子：7.196

摘要：Shape representation is a fundamental problem in computer vision. Current approaches to shape representation mainly focus on designing low-level shape descriptors which are robust to rotation, scaling and deformation of shapes. In this paper, we focus on mid-level modeling of shape representation. We develop a new shape representation called Bag of Contour Fragments (BCF) inspired by classical Bag of Words (BoW) model. In BCF, a shape is decomposed into contour fragments each of which is then individually described using a shape descriptor, e.g., the Shape Context descriptor, and encoded into a shape code. Finally, a compact shape representation is built by pooling shape codes in the shape. Shape classification with BCF only requires an efficient linear SVM classifier. In our experiments, we fully study the characteristics of BCF, show that BCF achieves the state-of-the-art performance on several well-known shape benchmarks, and can be applied to real image classification problem. HighlightsA new shape representation is proposed by encoding contour fragments in shape.The proposed shape representation is compact yet informative.The proposed shape representation is robust to shape deformation and conclusion.We obtain the state-of-the-art shape classification performance on several bench-mark datasets.