模式识别与人工智能
Sunday, Jan. 12, 2025 Home      About Journal      Editorial Board      Instructions      Ethics Statement      Contact Us                   中文
  2016, Vol. 29 Issue (9): 816-824    DOI: 10.16451/j.cnki.issn1003-6059.201609006
Researches and Applications Current Issue| Next Issue| Archive| Adv Search |
Image Automatic Segmentation Based on Fast Online Active Learning
YAN Jing, PAN Chen, YIN Haibing
College of Information Engineering, China Jiliang University, HangZhou 310018

Download: PDF (1393 KB)   HTML (1 KB) 
Export: BibTeX | EndNote (RIS)      
Abstract  An algorithm for image segmentation is proposed by building a pixels classification model. The model is trained online fast with a feed-forward neural network. Firstly, saliency map is computed by spectral residual (SR) approach. Then, multi-scale analysis is conducted via dispersion of minority high saliency points, and saliency map and gaze areas highly matching with human visual system are obtained. Next, positive and negative samples are selected randomly from saliency and non-saliency regions to compose the training set. A two-class random weighted feed-forward neural network model is trained. Finally, whole image pixels are classified by this model, and image segmentation is realized. Experiments show that the proposed algorithm enhances the segmentation performance for salient object grounded on the spectral residual based method, and the segmentation results are close to human visual perception.
Key wordsImage Segmentation      Saliency Detection      Random Weighted Feed-Forward Neural Network     
Received: 26 October 2015     
About author:: YAN Jing, born in 1991, master student. Her research inte-
rests include machine vision and pattern recognition.PAN Chen(Corresponding author), born in 1966, Ph.D., professor. His research interests include machine vision, pattern recognition and medical image processing.YIN Haibing, born in 1974, Ph.D., professor. His research interests include video coding.)
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
YAN Jing
PAN Chen
YIN Haibing
Cite this article:   
YAN Jing,PAN Chen,YIN Haibing. Image Automatic Segmentation Based on Fast Online Active Learning[J]. , 2016, 29(9): 816-824.
URL:  
http://manu46.magtech.com.cn/Jweb_prai/EN/10.16451/j.cnki.issn1003-6059.201609006      OR     http://manu46.magtech.com.cn/Jweb_prai/EN/Y2016/V29/I9/816
Copyright © 2010 Editorial Office of Pattern Recognition and Artificial Intelligence
Address: No.350 Shushanhu Road, Hefei, Anhui Province, P.R. China Tel: 0551-65591176 Fax:0551-65591176 Email: bjb@iim.ac.cn
Supported by Beijing Magtech  Email:support@magtech.com.cn