Semantic Hierarchies for Recognizing Objects and Parts
Semantic Hierarchies for Recognizing Objects and Parts
复制标题
DOI：
10.1109/cvpr.2007.383086
复制
发表时间：
2007-06
期刊：
影响因子：
--
通讯作者：
B. Epshtein;S. Ullman
中科院分区：
文献类型：
--
作者：
B. Epshtein;S. Ullman
本文介绍了一种新的表示识别对象及其部件，语义层次结构的建设和使用。它的优点包括改进的分类性能，准确的检测和定位的对象部分和子部分，并明确识别每个对象部分的不同外观。语义层次结构算法首先构建一个最小的功能层次结构，并继续通过添加语义等价的代表每个节点，使用整个层次结构作为一个上下文，用于确定添加的功能的身份和位置。通过自底向上自顶向下的循环来获得部件检测。与以前的方法不同，语义层次结构学习表示所有级别的对象部分的可能外观的集合，以及它们的统计依赖关系。该算法是全自动的，实验表明，大大提高了识别的对象及其部分。
This paper describes the construction and use of a novel representation for the recognition of objects and their parts, the semantic hierarchy. Its advantages include improved classification performance, accurate detection and localization of object parts and sub-parts, and explicitly identifying the different appearances of each object part. The semantic hierarchy algorithm starts by constructing a minimal feature hierarchy and proceeds by adding semantically equivalent representatives to each node, using the entire hierarchy as a context for determining the identity and locations of added features. Part detection is obtained by a bottom-up top-down cycle. Unlike previous approaches, the semantic hierarchy learns to represent the set of possible appearances of object parts at all levels, and their statistical dependencies. The algorithm is fully automatic and is shown experimentally to substantially improve the recognition of objects and their parts.