[1]夏敏 刘宏申.基于小波描述子和神经网络的形状识别[J].计算机技术与发展,2007,(03):106-108.
 XIA Min,LIU Hong-shen.The Shape Recognition System Based on Wavelet Descriptors and Neural Networks[J].,2007,(03):106-108.
点击复制

基于小波描述子和神经网络的形状识别()
分享到:

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2007年03期
页码:
106-108
栏目:
智能、算法、系统工程
出版日期:
1900-01-01

文章信息/Info

Title:
The Shape Recognition System Based on Wavelet Descriptors and Neural Networks
文章编号:
1673-629X(2007)03-0106-03
作者:
夏敏 刘宏申
安徽工业大学计算机学院
Author(s):
XIA Min LIU Hong-shen
School of Computer Science, Anhui University of Technology
关键词:
形状识别小波描述子多层感知器BP算法
Keywords:
shape recognitionwavelet descriptorsmultilayer perceptron BP algorithm
分类号:
TN911.73
文献标志码:
A
摘要:
提出一种把小波描述子和神经网络相结合的形状识别方法。通过小波描述子提取待识别物体的形状特征,所提取的特征值不受物体位移、缩放和旋转的影响,接着用多层分类器网络对物体的形状进行识别分类,并采用BP算法对神经网络进行学习和训练。最后得出令人满意的实验结果
Abstract:
The application of combining wavelet and neural networks to the 2 - D pattern recognition on the basis of its shape is presented, First, use wavelet descriptors to extract the shape features. The wavelet descriptors provide the appropriate invariances to the scale, rotation and translation. Then use neural networks to recognize and classify the shape of the 2 - D patterns, The type of neural networks is the multilayer perceptron. The shape recognitions systems constructed neural networks carry out studying and training by using the BP algorithm, Finally, a very good experiment result is obtained

相似文献/References:

[1]赵青 唐英敏.基于图形识别的汉字笔画分类方法[J].计算机技术与发展,2009,(10):14.
 ZHAO Qing,TANG Ying-min.Shape Recognition- Based Approach to Chinese Character Strokes' Classification[J].,2009,(03):14.

备注/Memo

备注/Memo:
安徽省教育厅自然科学基金项目(2006KJ018A)夏敏(1977-),女,安徽马鞍山人,硕士研究生,研究方向为计算机图像处理;刘宏申,教授,研究方向为计算机图像处理、模式识别
更新日期/Last Update: 1900-01-01