.png){kind=icon}
返回
Learning spatial relations in object recognition
.png){kind=icon}
OA
AI
DOI：10.1016/j.patrec.2006.03.016.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
This paper studies two types of spatial relationships that can be learned from training examples for object recognition. The first one employs deformable relationships between object parts with a Gaussian model, while the second one describes pairwise relationships between pixel intensity values using Bayesian networks. We perform experiments on a human face dataset and a horse dataset, imposing the same amount of annotation of training data, which can be seen as sending knowledge to the learning algorithms. The result indicates that the Bayesian network method compares favorably to the deformable model, as it can capture long-distance stable relations in the object appearance. We also conclude that both methods are superior to strictly spatial matching by template and strictly non-spatial classifiers. (c) 2006 Elsevier B.V. All rights reserved.
Keyword:
articulated object
Bayesian network
deformable model
part-based approach
shape
spatial relation
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。