期刊文献+

基于小波矩和SCNN的多目标图像识别

Multi-objects Recognition Based on Wavelet Invariant Moment and Self-organized Competitive Neural Network
下载PDF
导出
摘要 提出了将自组织竞争人工神经网络(SCNN)和小波矩结合进行图像旋转不变识别的新方法。SCNN可以克服反向传播神经网络(BPN)不易收敛、低效率等缺点,而且小波矩方法提取的图像不变矩特征具有很强的辨别力和抗噪性能。计算机模拟显示该方法使用简单、效率高,具有很好的研究价值。 Because Back-propagation Neural Network(BPN) has the shortcomings of bad convergence and low efficiency,and Self-organized Competitive Neural Network (SCNN) can overcome these shortcomings.The wavelet invariant moment possess good recognition and anti-noise capacity.So a new method of Distortion Invariant Pattern Recognition (DIPR) based on Self-organized Competitive Neural Network(SCNN) and wavelet invafiant moments is proposed.By using the proposed method,the results of computer simulation show this method is useful and efficiency.
出处 《计算机工程与应用》 CSCD 北大核心 2006年第17期90-92,104,共4页 Computer Engineering and Applications
关键词 自组织竞争人工神经网络 反向传播神经网络 小波矩 旋转不变矩 多目标识别 Self-organized Competitive Neural Network (SCNN), Back-propagation Neural Network (BPN),wavelet invariant moment,rotation invariant moment,multi-objects recognition
  • 相关文献

参考文献11

二级参考文献69

  • 1杨百愚,冯大毅.确定圆谐滤波器展开中心的方法[J].光电子技术与信息,2005,18(3):62-66. 被引量:3
  • 2周杰,彭嘉雄,丁明跃.基于小波特征的图像匹配方法[J].模式识别与人工智能,1996,9(2):125-129. 被引量:10
  • 3徐丽娜.神经网络控制[M].哈尔滨:哈尔滨工业大学出版社,1998.. 被引量:20
  • 4Hu M K.Visual pattern recognition by moment invariants[J].IRE Trans on Info Theory, 1962; (8): 179~187 被引量:1
  • 5Teague M.Image analysis via the general theory of moments[J].J Opt Soc Am, 1980; (70) :920~930 被引量:1
  • 6Cho Huak The,Roland T Chin. On image analysis by the methods of moments[J].IEEE Transcation on Pattern Analysis and Machine Intelligence, 1988; (10) :496~513 被引量:1
  • 7Dinggang Shen,Horace H d Ip.Discriminative wavelet shape descriptors for recognition[J].Pattern Recognition, 1999; (32): 151~165 被引量:1
  • 8Kan Chao,Srinath M D.Combined features of cubic B-spline wavelet moments and Zernike moments for invariant character recognition[J].Information Technology,2001 ;4(2) :511~515 被引量:1
  • 9Alireza Khotanzad,Yaw Hua Hong. Invariant image recognition by Zernike moments[J].IEEE Transcation on Pattern Analysis and Machine Intelligence, 1990; 5 (12): 489~497 被引量:1
  • 10张延炘.人工神经网络及其光学实现[J].光电子.激光,1990,1(1):1-11. 被引量:2

共引文献78

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部