| 用神经网络鉴别退化图像的模糊类型 |
| |
| 引用本文： | 尹兵,王延斌,刘威.用神经网络鉴别退化图像的模糊类型[J].光学技术,2006,32(1):138-140. |
| |
| 作者姓名： | 尹兵 王延斌 刘威 |
| |
| 作者单位： | 1. 北京理工大学,信息科学技术学院光电工程系,北京,100081
2. 北京华北光学仪器有限公司,北京,100050 |
| |
| 摘 要： | 提出了一种用神经网络鉴别退化图像的模糊类型的方法。由于采用不同降质方法得到退化图像的频谱差异较大,以此作为判别依据,用概率神经网络实现了对四种模糊类型:离焦,矩形,运动和高斯模糊的鉴别。根据神经网络的鉴别结果决定点扩散函数的初始估计值,可大大地提高盲解恢复算法的复原质量和系统点扩散函数的估计精度,扩大了算法的实用范围。
|
| 关 键 词： | 神经网络 模糊 PSF 盲解卷积 频域 |
| 文章编号： | 1002-1582(2006)01-0138-03 |
| 收稿时间： | 2004/10/25 |
| 修稿时间： | 2004年10月25 |
Blur identification of the degraded images by neural network |
| |
| YIN Bing,WANG Yan-bin,LIU Wei.Blur identification of the degraded images by neural network[J].Optical Technique,2006,32(1):138-140. |
| |
| Authors: | YIN Bing WANG Yan-bin LIU Wei |
| |
| Abstract: | An original solution of the blur identification problem was presented.Because the certain blur leads to the specific distortion of the image Fourier spectrum amplitude.According to this,a neural network based on probability was used for the blur identification.Four types of blur were considered: gaussian,rectangular,motion and defocus ones.Using neural network's output as the preliminary estimation of the PSF in the blind deconvolution algorithm can significantly improve restored images' quality and the precision of the PSF.This method also expands the application of blind deconvolution algorithms. |
| |
| Keywords: | neural network blur PSF blind deconvolution frequency domain |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
