用细胞神经网络实现图像恢复的一种新方法
A NEW APPROACH FOR IMAGE RESTORATION BASED ON CELLULAR NEURAL NETWORK
-
摘要: 文中提出并讨论了用细胞神经网络实现图象最大熵恢复的可能性，并基于对最大熵方法的物理实质分析推出了相应细胞神经网络模板的新设计方法，针对二值图象的恢复问题进行了计算机仿真，结果证明了这一方法是可行的。
-
关键词:
- 最大嫡图像恢复;细胞神经网;模板设计法
Abstract: A new approach for image restoration based on Cellular Neural Network(CNN) is proposed. The physical meaning of Maximum Entropy (ME) is analyzed and a new template is proposed for ME binary image restoration. The result of computer simulation proves this approach is reasonable. -
Chua L O, Yang L. Cellular neural network: Theory. IEEE Trans. on CAS, 1988, CAS-35(10)[2]57-1272.[3]Chua L O, Yang L. Cellular neural network: Applications. IEEE Trans. on CAS, 1988, CAS-[4](10): 1273-1290.[5]Venetianer P L, Werblin F, Roska T, Chua L O. Analogic CNN algorithms for some image[6]compression and restoration tasks. IEEE Trans. on CAS, 1995, CAS-42(5): 278-284.[7]Sziranyi T, Zerubia J. Markov random field image segmentation using CNN. IEEE Trans. on[8]CAS, 1997, CAS-44(1): 86-89.[9]曾朝辉.CNN在图像处理中的应用:[硕士论文1，北京:北京大学电子学系，1995.[10]Derin H, Elliot H. Modeling and segmentation of noisy textured image using GRF. IEEE Trans.[11]on PAMI, 1987, PAMI-9(1): 39-55.[12]Trussel H. The relationship between image restoration by the MAP method and a ME method.[13]IEEE Trans. on ASSP, 1980, ASSP-28(1): 114-117.[14]周新伦.数字图像处理.北京:国防工业出版社，1986, 174-179.[15]Proc. IEEE Intl. Conf. Cellular Neural Network and Their Applications, CNNA-94, 1994, 3-8. -
计量
- 文章访问数: 1956
- HTML全文浏览量: 111
- PDF下载量: 645
- 被引次数: 0
下载:
