Spatial relationship representation for visual object searching
Spatial relationship representation for visual object searching
复制标题
DOI：
10.1016/j.neucom.2007.11.030
复制
发表时间：
2008-06
期刊：
影响因子：
6
通讯作者：
Jun Miao;Lijuan Duan;Laiyun Qing;Wen Gao;Xilin Chen;Yuan Yuan-Yuan
中科院分区：
文献类型：
--
作者：
Jun Miao;Lijuan Duan;Laiyun Qing;Wen Gao;Xilin Chen;Yuan Yuan-Yuan
多年来，图像表示一直是视觉研究的关键问题。为了有效地表示各种局部图像模式或物体，研究这些物体之间的空间关系非常重要，特别是为了在其中搜索特定物体。心理学实验支持了人类利用视觉背景或物体空间关系来认知世界的假设。如何高效地学习和记忆这些知识是一个值得研究的关键问题。本文提出了一种新型神经网络，通过稀疏编码来学习和记忆物体空间关系。进行了一组在几个稀疏特征之间进行视觉对象搜索的比较实验来检验所提出的方法。分析和讨论了空间关系稀疏编码的效率。理论和实验结果表明，新发展的神经网络能够很好地学习和记忆物体空间关系，同时视觉上下文的学习和记忆无疑成为模拟人类视觉系统的巨大挑战。
Image representation has been a key issue in vision research for many years. In order to represent various local image patterns or objects effectively, it is important to study the spatial relationship among these objects, especially for the purpose of searching the specific object among them. Psychological experiments have supported the hypothesis that humans cognize the world using visual context or object spatial relationship. How to efficiently learn and memorize such knowledge is a key issue that should be studied. This paper proposes a new type of neural network for learning and memorizing object spatial relationship by means of sparse coding. A group of comparison experiments for visual object searching between several sparse features are carried out to examine the proposed approach. The efficiency of sparse coding of the spatial relationship is analyzed and discussed. Theoretical and experimental results indicate that the newly developed neural network can well learn and memorize object spatial relationship and simultaneously the visual context learning and memorizing have certainly become a grand challenge in simulating the human vision system.