-
在图像去噪过程中, 大部分基于偏微分方程的各向异性扩散模型均使用梯度信息检测边缘, 当边缘部分被噪声严重污染时, 这些方法不能有效检测出这些边缘, 因而无法保留边缘特征. 为了较完整的保留图像的区域信息, 用脉冲耦合神经网络(PCNN)能使具有相似输入的神经元同时产生脉冲的性质对噪声图像做处理, 得到图像熵序列, 并将图像熵序列作为边缘检测算子引入到扩散方程中, 不仅能克服仅用梯度作为边缘检测算子易受噪声影响的弊端, 而且能较完整地保留图像的区域信息. 然后, 用最小交叉熵准则搜索使去噪前后图像信息量差异最小的阈值, 设计最佳阈值控制扩散强度, 建立基于脉冲耦合神经网络与图像熵改进的各向异性扩散模型(PCNN-IEAD). 分析与仿真结果表明, 该模型与经典模型相比, 保留了更多的图像信息, 能够兼顾去除图像的噪声和保护图像的边缘纹理等细节信息, 较完整的保留了图像的区域信息, 性能指标同样也证实了新模型的优越性. 另外, 该模型的运行时间较经典模型的短, 因此, 该模型是一个理想的模型.In image processing, most of the anisotropic diffusion models based on partial differential equation use gradient information to detect image edge. If the image edge is seriously polluted by noise, these methods would not be able to detect image edge, so the edge features cannot be retained. Pulse coupled neural network (PCNN) has the property that similar input neurons can generate pulse at the same time; this property is used to process the noisy image, and we can get an image entropy sequence. The image entropy sequence which will be used as an edge detecting operator is introduced into the diffusion equation, and this will not only reduce the defects produced when the gradient is used as an edge detecting operator so it is easily affected by the noise, but the area image information can also retain more completely. Then, we will use the rule of minimum cross entropy to search for a minimum threshold, which would satisfy the condition that the information difference between noisy image and denoised image is the minimum. The optimal threshold designed will control diffusion intensity reasonably, and the anisotropic diffusion model based on pulse coupled neural network and image entropy (PCNN-IEAD) can be established. Analysis and simulation results show that the proposed model preserves more image information than the classical ones. It removes the image noise and at the same time protects the edge texture details of the image; the proposed model retains the area image information more completely, the performance indexes can also confirm the superiority of the new model. In addition, the operating time of the proposed model is shorter than that of the classical models, therefore, the proposed model may be the ideal one.
[1] Zhang W, Li J J, Yang Y P 2014 Signal Process 103 6
[2] Chumchob N 2013 IEEE Trans. Image Process 22 4551
[3] Wu T T, Yang Y F, Pang Z F 2012 Appl. Numer. Math. 62 79
[4] Wu J, Tang C 2011 IEEE Trans. Image Process 20 2428
[5] Brito-Loeza C, Chen K 2010 IEEE Trans. Image Process 19 1518
[6] Wang Z, Huang X, Li Y X, Song X N 2013 Chin. Phys. B 22 010504
[7] Perona P, Malik J 1990 IEEE Trans. Pattern Anal. Mach. Intell. 12 629
[8] Rudin L I, Osher S, Fatemi E 1992 Physica D 60 259
[9] Cheng L Y, Tang C, Yan S 2011 Optics Communications 284 5549
[10] Liu P, Fang H, Li G Q, Liu Z W 2012 IEEE Geosci. Remote Sens. 9 358
[11] Niang O, Thioune A, Gueirea M C 2012 IEEE Trans. Image Process 21 3991
[12] Bumsub H, Dongbo M, Kwanghoon So 2013 IEEE Trans. Image Process 22 1096
[13] Zhou X C, Wang M L, Zhou L F, Wu Q 2015 Acta Phys. Sin. 64 024205(in Chinese) [周先春, 汪美玲, 周林锋, 吴琴 2015 物理学报 64 024205]
[14] Zhou X C, Shi L F, Han X L, Mo J Q 2014 Chin. Phys. B 23 090204
[15] Zhou X C, Shi L F, Mo J Q 2014 Chin. Phys. B 23 040202
[16] Zhang Y H, Ding Y, Wang L H 2011 Procedia Engineering 15 2778
[17] Li J C, Ma Z H, Peng Y X, Huang B 2013 Acta Phys. Sin. 62 099501(in Chinese) [李金才, 马自辉, 彭宇行, 黄斌 2013 物理学报 62 099501]
[18] Zhang K K, Gao X B, Li X L 2012 IEEE Trans. Image Process 21 4544
[19] Dabov K, Foi A, Katkovnik V, Egiazarian K 2007 IEEE Trans. Image Process 16 2080
[20] Deledalle C A, Denis L, Tupin F 2009 IEEE Trans. Image Process 18 2661
[21] Nikpour M, Hassanpour H 2010 IET Image Process 4 452
[22] Kamilov, Bostan E, Unser M 2012 IEEE Signal Process Lett. 19 187
[23] Johnson J L, Padgett M L 1999 IEEE Trans. Neural Netw. 10 480
[24] Ranganath H S, Kuntimad G 1999 IEEE Trans. Neural Netw. 10 615
[25] Weickert J, Bary H R, Max A V 1998 IEEE Trans. Image Process 7 398
[26] Canny J 1986 IEEE Trans. Pattern Anal. Mach. Intell. PAMI-8 679
-
[1] Zhang W, Li J J, Yang Y P 2014 Signal Process 103 6
[2] Chumchob N 2013 IEEE Trans. Image Process 22 4551
[3] Wu T T, Yang Y F, Pang Z F 2012 Appl. Numer. Math. 62 79
[4] Wu J, Tang C 2011 IEEE Trans. Image Process 20 2428
[5] Brito-Loeza C, Chen K 2010 IEEE Trans. Image Process 19 1518
[6] Wang Z, Huang X, Li Y X, Song X N 2013 Chin. Phys. B 22 010504
[7] Perona P, Malik J 1990 IEEE Trans. Pattern Anal. Mach. Intell. 12 629
[8] Rudin L I, Osher S, Fatemi E 1992 Physica D 60 259
[9] Cheng L Y, Tang C, Yan S 2011 Optics Communications 284 5549
[10] Liu P, Fang H, Li G Q, Liu Z W 2012 IEEE Geosci. Remote Sens. 9 358
[11] Niang O, Thioune A, Gueirea M C 2012 IEEE Trans. Image Process 21 3991
[12] Bumsub H, Dongbo M, Kwanghoon So 2013 IEEE Trans. Image Process 22 1096
[13] Zhou X C, Wang M L, Zhou L F, Wu Q 2015 Acta Phys. Sin. 64 024205(in Chinese) [周先春, 汪美玲, 周林锋, 吴琴 2015 物理学报 64 024205]
[14] Zhou X C, Shi L F, Han X L, Mo J Q 2014 Chin. Phys. B 23 090204
[15] Zhou X C, Shi L F, Mo J Q 2014 Chin. Phys. B 23 040202
[16] Zhang Y H, Ding Y, Wang L H 2011 Procedia Engineering 15 2778
[17] Li J C, Ma Z H, Peng Y X, Huang B 2013 Acta Phys. Sin. 62 099501(in Chinese) [李金才, 马自辉, 彭宇行, 黄斌 2013 物理学报 62 099501]
[18] Zhang K K, Gao X B, Li X L 2012 IEEE Trans. Image Process 21 4544
[19] Dabov K, Foi A, Katkovnik V, Egiazarian K 2007 IEEE Trans. Image Process 16 2080
[20] Deledalle C A, Denis L, Tupin F 2009 IEEE Trans. Image Process 18 2661
[21] Nikpour M, Hassanpour H 2010 IET Image Process 4 452
[22] Kamilov, Bostan E, Unser M 2012 IEEE Signal Process Lett. 19 187
[23] Johnson J L, Padgett M L 1999 IEEE Trans. Neural Netw. 10 480
[24] Ranganath H S, Kuntimad G 1999 IEEE Trans. Neural Netw. 10 615
[25] Weickert J, Bary H R, Max A V 1998 IEEE Trans. Image Process 7 398
[26] Canny J 1986 IEEE Trans. Pattern Anal. Mach. Intell. PAMI-8 679
计量
- 文章访问数: 5497
- PDF下载量: 219
- 被引次数: 0