作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2011, Vol. 37 ›› Issue (21): 173-175. doi: 10.3969/j.issn.1000-3428.2011.21.059

• 人工智能及识别技术 • 上一篇    下一篇

自然图像中的感兴趣目标检测技术

赵 倩1,2,胡越黎1,曹家麟1,2   

  1. (1. 上海大学机电工程与自动化学院,上海 200072;2. 上海电力学院电子科学与技术系,上海 200090)
  • 收稿日期:2011-06-17 出版日期:2011-11-05 发布日期:2011-11-05
  • 作者简介:赵 倩(1969-),女,副教授、博士研究生,主研方向:数字图像处理,机器视觉;胡越黎、曹家麟,教授、博士生导师
  • 基金资助:
    国家自然科学基金资助项目(60902085);上海市教育委员会科研创新基金资助项目(10ZZ118)

Object of Interest Detection Technology in Natural Image

ZHAO Qian 1,2, HU Yue-li 1, CAO Jia-lin 1,2   

  1. (1. School of Mechatronics Engineering and Automation, Shanghai University, Shanghai 200072, China; 2. Department of Electronic Science and Technology, Shanghai University of Electric Power, Shanghai 200090, China)
  • Received:2011-06-17 Online:2011-11-05 Published:2011-11-05

摘要: 基于显著图的目标检测方法不能精确地找到感兴趣目标的位置,或在同一感兴趣目标上检测出多个感兴趣区域。为此,提出一种视觉注意机制和模糊支持向量机(FSVM)相结合的算法。根据显著度和角点分布信息,从图像中获得包括单个目标的视觉窗口,并在窗口中采用FSVM算法分割目标和背景。实验结果表明,该方法符合生物的视觉注意机制,分割效果较好。

关键词: 感兴趣目标, 显著图, 模糊支持向量机, 视觉注意, 特征提取

Abstract: Saliency map based the Region of Interesting(ROI) detection often has the problems of not able to locate object of interesting accurately and that many interesting object can be detected on the same ROI. A new technique for detecting regions of interest in a natural image by using visual attention model and Fuzzy Support Vector Machine(FSVM) is proposed. A visual window including single object is created according to the visual attention and edge information based on distribution of corner points from an image. By using FSVM based on affinity among samples, it can extract single object in the visual window. Experimental results show that it coincides with human visual attention mechanism and demonstrate the effectiveness of the proposed approach.

Key words: object of interest, saliency map, Fuzzy Support Vector Machine(FSVM), visual attention, feature extraction

中图分类号: