.png){kind=icon}
返回
Occluded objects recognition using multiscale features and Hopfield neural network
.png){kind=icon}
PRE
AI
DOI：10.1016/S0031-3203(96)00061-1.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
A new method to recognize partially visible two-dimensional objects by means of multiscale features and Hopfield neural network was proposed. The Hopfield network was employed to perform global feature matching. Since the network only guarantees to converge to a local optimal state, the matching results heavily depend on the initial network state determined by the extracted features. To acquire more satisfactory initial matching results, a new feature vector was developed which consists of the multiscale evolution of the extremal position and magnitude of the wavelet transformed contour orientation. These features can even be used to discriminate dominant points, hence good initial states can be obtained. The good initiation enables our proposed method to recognize objects even heavily occluded, that cannot be achieved by using the Nasrabadi-Li's method. In addition, to make the matching results more insensitive to the threshold value selection of the network, we replace the step-like thresholding function by a ramp-like one. Experimental results have shown that our method is effective even for noisy occluded objects. Copyright (C) 1996 Pattern Recognition Society.
Keyword:
wavelet transformed extremal evolution
dominant points
integrated multiscale features
hopfield neutral network
feature matching
occluded objects recognition
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。
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
暂无机构信息
引用论文
Risk and Protective Factors for Family Violence among Low-Income Fathers: Implications for Violence Prevention and Fatherhood Programs.png)
Social Work
Social WorkIF0
PREAI
分享收藏
查看更多内容