首页 | 本学科首页   官方微博 | 高级检索  
     


An MLP-based texture segmentation method without selecting a feature set
Authors:U Bhattacharya  BB Chaudhuri  SK Parui
Affiliation:

Computer Vision and Pattern Recognition Unit, Indian Statistical Institute, 203, Barrackpore Trunck Road, Calcutta, 700 035, India

Abstract:A texture segmentation technique which employs a multilayer perceptron (MLP) and does not consider the selection of features is presented in this paper. Thus, users can avoid selection and computation of the feature set and hence real-time segmentation may be possible. The technique apparently works in a fashion similar to our visual system whereby we do not consciously compute any feature for texture discrimination. A detailed study has been made for the selection of the network size. A newly proposed variant of the back-propagation algorithm has been used for more efficient training of the network. An edge-preserving noise-smoothing approach has been proposed to remove noise from the segmented image.
Keywords:Texture segmentation  Multilayer perceptron  Modified backpropagation  Feature extraction
本文献已被 ScienceDirect 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号