| 基于Zernike矩和BP神经网络的纹理分割 |
| |
| 引用本文： | 李海啸,姜璐,舒华忠.基于Zernike矩和BP神经网络的纹理分割[J].东南大学学报(自然科学版),2005,35(2):199-201. |
| |
| 作者姓名： | 李海啸 姜璐 舒华忠 |
| |
| 作者单位： | 东南大学影像科学与技术实验室,南京,210096 |
| |
| 摘 要： | 提出了一种基于Zernike矩和BP神经网络的纹理分割方法.对图像的每个像素,选择一个窗口,计算该窗口内的Zernkie矩,然后通过非线性变换器将得到的矩值转换成纹理特征;选择BP神经网络作为分类器,将图像的每个像素得到的n维特征向量输入BP神经网络进行分类,最后将结果标注在原图像上.和基于Legendre矩的纹理分割结果相比,基于Zernike矩的纹理分割可以降低分割错误率.
|
| 关 键 词： | Zernike矩 BP神经网络 纹理分割 纹理分析 |
| 文章编号： | 1001-0505(2005)02-0199-03 |
Texture segmentation based on Zernike moment and BP neural network |
| |
| Li Haixiao,JIANG Lu,Shu Huazhong.Texture segmentation based on Zernike moment and BP neural network[J].Journal of Southeast University(Natural Science Edition),2005,35(2):199-201. |
| |
| Authors: | Li Haixiao JIANG Lu Shu Huazhong |
| |
| Abstract: | A texture segmentation algorithm based on Zernike moment and BP neural network is presented. The Zernike moments in small local windows of each pixel in the image are computed first and a nonlinear transducer is used to map the moments to texture features which are then inputted to BP neural network for classifying. Compared with the segmentation results based on Legendre moment, the Zernike moment based algorithm can reduce the error rates. |
| |
| Keywords: | Zernike moment BP neural network texture segmentation texture analysis |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
