基于空间约束高斯混合模型的EPLL自然图像复原

J4 ›› 2015, Vol. 32 ›› Issue (4): 391-398.

基于空间约束高斯混合模型的EPLL自然图像复原

廖斌,刘鸳鸳

湖北大学计算机与信息工程学院，湖北武汉430062

收稿日期:2014-08-26 修回日期:2014-09-28 出版日期:2015-07-28 发布日期:2015-08-04
通讯作者: 廖斌（1979-），湖北人，副教授，博士，从事计算机图像视频处理的研究. E-mail:bliao@hubu.edu.cn
基金资助:
国家自然科学基金资助(61300125)

EPLL based Natural Image Restoration using Spatially Constrained Gaussian Mixture Model

Liao Bin, Liu Yuanyuan

School of Computer Science and Information Engineering, Hubei University, Wuhan 430062, China

Received:2014-08-26 Revised:2014-09-28 Published:2015-07-28 Online:2015-08-04

摘要/Abstract

摘要：

为了提高基于块先验的自然图像复原效果，有效去除图像中的噪声和模糊，提出了一种基于空间约束高斯混合模型的块似然对数期望(Expected Patch Log Likelihood, EPLL)复原框架。基于图像块的空间分布信息，将图像块的空间约束高斯混合统计特性作为先验，在图像块复原的基础上实现整幅图像的全局优化复原。对比相关的图像复原方法，提出的方法去噪和去模糊效果更好，并且保图像细节。利用客观性能指标对复原结果进行评价。实验结果表明，提出的方法有效易行，而且复原图像表现出良好的可视效果。

关键词: 图像处理, 图像复原, 空间约束高斯混合模型, 先验, 块似然对数期望

Abstract:

In order to improve the performance of patch prior based natural image restoration, effectively remove the noise and blur of images, a restoration framework of Expected Patch Log Likelihood (EPLL) using spatially constrained gauss mixture model was presented. Based on the spatial distribution information of patches, the spatially constrained gauss mixture statistical characteristics of image patches were as the priors to reach image patch restoration. Image restoration was realized based on the global optimization of image patch restoration. Compared with related works, the proposed method performed better in image denoising and deblurring, and preserved details. The performance of the restoration results was evaluated by the objective indicator. The experimental results show that the proposed method is effective and the visual effect of the image restoration is pleased.

Key words: image processing, image restoration, spatially constrained gaussian mixture model, prior, EPLL

廖斌刘鸳鸳. 基于空间约束高斯混合模型的EPLL自然图像复原[J]. J4, 2015, 32(4): 391-398.

Liao Bin, Liu Yuanyuan . EPLL based Natural Image Restoration using Spatially Constrained Gaussian Mixture Model[J]. J4, 2015, 32(4): 391-398.

参考文献

[1] J. Portilla, V. Strela, M. Wainwright, and E. Simoncelli, “Image denoising using scale mixtures of gaussians in the wavelet domain,” IEEE Transactions on Image Processing, vol. 12, no. 11, pp. 1338–1351, 2003.
[2] A. Buades, B. Coll, and J. Morel, “A non-local algorithm for image denoising,” in Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on, vol. 2, pp. 60–65, IEEE, 2005.
[3] M. Elad and M. Aharon, “Image denoising via sparse and redundant representations over learned dictionaries,” Image Processing, IEEE Transactions on, vol. 15, no. 12, pp. 3736–3745, 2006.
[4] Y. Hel-Or and D. Shaked, “A discriminative approach for wavelet denoising,” IEEE Transactions on Image Processing, vol. 17, no. 4, p. 443, 2008.
[5] K. Dabov, A. Foi, V. Katkovnik, and K. Egiazarian, “Image restoration by sparse 3D transform-domain collaborative filtering,” in SPIE Electronic Imaging, 2008.
[6] S. Roth and M. Black, “Fields of experts,” International Journal of Computer Vision, vol. 82, no. 2, pp. 205–229, 2009.
[7] D. Krishnan and R. Fergus, “Fast image deconvolution using hyper-laplacian priors,” in Advances in Neural Information Processing Systems 22, pp. 1033–1041, 2009.
[8] J. Mairal, F. Bach, J. Ponce, G. Sapiro, and A. Zisserman, “Non-local sparse models for image restoration,” in Computer Vision, 2009 IEEE 12th International Conference on, pp. 2272–2279, IEEE, 2010.
[9]? Daniel Zoran, Yair Weiss: From learning models of natural image patches to whole image restoration. ICCV 2011: 479-486
[10]?Thanh Minh Nguyen, Q. M. Jonathan Wu: Fast and Robust Spatially Constrained Gaussian Mixture Model for Image Segmentation. IEEE Trans. Circuits Syst. Video Techn. 23(4): 621-635 (2013)
[11] D. Geman and C. Yang, “Nonlinear image recovery with half-quadratic regularization,” Image Processing, IEEE Transactions on, vol. 4, no. 7, pp. 932–946, 2002.
[12] D. Martin, C. Fowlkes, D. Tal, and J. Malik, “A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics,” in Proc. 8th Int’l Conf. Computer Vision, vol. 2, pp. 416–423, July 2001.

[1]	於康杰, 方波, 李剑敏, 王震, 蔡晋辉, 邬佳璐, 何正龙 . 太赫兹成像三维块匹配自适应Canny边缘检测算法[J]. 量子电子学报, 2023, 40(4): 458-468.
[2]	葛宏义 , 王飞 , 蒋玉英 , 李丽 , 张元 , 贾柯柯 , . 基于宽度学习的太赫兹光谱图像小麦霉变识别研究[J]. 量子电子学报, 2023, 40(3): 360-368.
[3]	杜天宇, 高昆∗ , 吴朝. 光栅相衬 CT 中吸收信号环形伪影的去除方法[J]. 量子电子学报, 2023, 40(1): 40-47.
[4]	陈建明, , 曾祥津, , 钟丽云, , 邸江磊, ∗ , 秦玉文, ∗. 基于深度学习的图像配准方法研究进展综述[J]. 量子电子学报, 2022, 39(6): 899-926.
[5]	吴琼, 马雷∗. 一种基于 LoG 算子的量子图像边缘检测算法[J]. 量子电子学报, 2022, 39(5): 720-727.
[6]	杨一杉, 梁华为, 姚瑶, 陈帅∗. 金属遮挡条件下光子层析快速重构方法研究[J]. 量子电子学报, 2022, 39(4): 558-565.
[7]	张杨∗, 程正东, 朱斌. 基于改进 Faster R-CNN 的无人机小目标检测算法[J]. 量子电子学报, 2022, 39(3): 354-363.
[8]	毛仁祥, 常建华, 张树益李红旭, 张露瑶. 基于3D-MobileNetv2 的多目标实时跟踪框架[J]. 量子电子学报, 2022, 39(3): 364-372.
[9]	臧一鸣, 朱尚超, 魏战红∗, 刘志飞, 林小竹, 孙文韬. 一种量子图像伪彩色编码方法[J]. 量子电子学报, 2022, 39(3): 343-353.
[10]	洪富祥, 陈冲, 丘仲锋∗. 一种基于机器视觉的无人机同心圆靶精准降落方法[J]. 量子电子学报, 2021, 38(3): 307-315.
[11]	陈儒, 杨义勤, 秦凡凯, 孟昭晖, 苗昕扬, 赵昆, 詹洪磊∗. 样本内部缺陷的太赫兹光谱成像与算法优化[J]. 量子电子学报, 2021, 38(3): 265-271.
[12]	王昱皓, 唐泽恬, 钟岷哲, 王阳, 曾瑞敏, 朱登玮, 杨晨. 基于相位相关和纹理分类的SIFT 图像拼接算法[J]. 量子电子学报, 2020, 37(6): 650-658.
[13]	王振武, 高隽, 范之国, 王昕, 张强. 利用正交偏振信息的透玻透膜成像方法[J]. 量子电子学报, 2019, 36(6): 691-698.
[14]	汪炜怡, 徐青山, 杨明翰. 基于光学灰度图像辨识的系统故障诊断方法[J]. 量子电子学报, 2019, 36(6): 699-704.
[15]	钱江，方勇华，吴军. 基于单幅图像的雾霾图像快速还原方法[J]. 量子电子学报, 2019, 36(4): 402-407.