基于泰勒展开式与曲率逆向驱动的图像超分辨算法

计算机应用 ›› 2014, Vol. 34 ›› Issue (12): 3570-3575.

基于泰勒展开式与曲率逆向驱动的图像超分辨算法

赵小乐¹,吴亚东¹,张红英²,赵静³

1. 西南科技大学计算机科学与技术学院,四川绵阳 621010；
2. 西南科技大学信息工程学院,四川绵阳 621010
3. 四川大学计算机(软件)学院,成都 610045

收稿日期:2014-06-20 修回日期:2014-08-08 出版日期:2014-12-01 发布日期:2014-12-31
通讯作者: 赵小乐
作者简介:赵小乐(1987-),男,四川南部人,硕士研究生,主要研究方向:数字图像处理；吴亚东(1979-),男,河南周口人,教授,博士,主要研究方向:图像图形处理、信息可视化、人机交互；张红英(1976-),女,四川德阳人,教授,博士,主要研究方向:数字图像处理；赵静(1991-),女,四川隆昌人,硕士研究生,主要研究方向:数字图像处理。
基金资助:
国家自然科学基金资助项目;国家科技支撑计划项目;四川省科技厅青年人才培养计划项目;四川省科技厅重点项目;四川省教育厅重点项目

Reverse curvature-driven super-resolution algorithm based on Taylor formula

ZHAO Xiaole¹,WU Yadong¹,ZHANG Hongying²,ZHAO Jing³

1. School of Computer Science and Technology, Southwest University of Science and Technology, Mianyang Sichuan 621010, China;
2. School of Information Engineering, Southwest University of Science and Technology, Mianyang Sichuan 621010, China;
3. College of Computer (Software), Sichuan University, Chengdu Sichuan 610045, China

Received:2014-06-20 Revised:2014-08-08 Online:2014-12-01 Published:2014-12-31
Contact: ZHAO Xiaole

摘要/Abstract

摘要：

针对传统的插值算法和基于模型的超分辨算法通常会导致图像对比度和清晰度下降等问题,提出了一种基于泰勒展开式与曲率逆向驱动图像超分辨算法。该算法首先采用泰勒公式估计图像灰度值的变化趋势,然后利用等照度线的曲率细化图像边缘特征,并将梯度作为约束条件抑制图像边缘的锯齿与振铃效应。大量实验表明,所提算法在清晰度和信息保留度上比传统算法更具有优势,算法处理结果更符合人眼视觉效果,在泰勒展开式的基础上进行逆向扩散也使该算法的运行效率明显高于传统迭代算法。

Abstract:

To solve the problem of traditional interpolation and model-based methods usually leading to decrease of the contrast and sharpness of images, a reverse curvature-driven Super-Resolution (SR) algorithm based on Taylor formula was proposed. The algorithm used the Taylor formula to estimate the change trend of image intensity, and then the image edge features were detailed by the curvature of isophote. Gradients were used as constraints to inhibit the jagged edges and ringing effects. The experimental resluts show that the proposed algorithm has obvious advantages over the conventional interpolation algorithm and model-based methods in clarity and information retention, and its result is more in line with human visual effects. The proposed algorithm is more effective than traditional iterative algorithms for reverse diffusion based on Taylor expansion is implemented.

中图分类号:

TP391

赵小乐吴亚东张红英赵静. 基于泰勒展开式与曲率逆向驱动的图像超分辨算法[J]. 计算机应用, 2014, 34(12): 3570-3575.

ZHAO Xiaole WU Yadong ZHANG Hongying ZHAO Jing. Reverse curvature-driven super-resolution algorithm based on Taylor formula[J]. Journal of Computer Applications, 2014, 34(12): 3570-3575.

参考文献

［1］UNGER M, POCK T, WERLBERGER M, et al. A convex approach for variational super-resolution［C］// DAGM 2010: Annual Symposium of the German Association for Pattern Recognition. Berlin: Springer, 2010: 313-322.
［2］BABACAN S D, MOLINA R, KATSAGGELOS A K. Variational Bayesian super resolution［J］. IEEE Transactions on Image Processing, 2011, 20(4): 984-999.
［3］CHANTAS G, GALATSANOS N P, MOLINA R, et al. Variational Bayesian image restoration with a product of spatially weighted total variation image priors［J］. IEEE Transactions on Image Processing, 2010, 19(2): 351-362.
［4］BABACAN S, MOLINA R, KATSAGGELOS A. Parameter estimation in TV image restoration using variational distribution approximation［J］. IEEE Transactions on Image Processing, 2008, 17(3):326-339.
［5］KASS M, WITKIN A, TERZOPOULOS D. Snakes: Active contour models［J］. International Journal of Computer Vision, 1988, 1(4): 321-331.
［6］LU J, ZHANG Q, XU Z, et al. A fast curvature-driven image interpolation method similar to bilinear［J］. Opto-Electronic Engineering, 2011, 38(4):108-114. (路锦正, 张启衡, 徐智勇, 等. 基于曲率驱动的类双线性图像快速插值方法［J］. 光电工程, 2011, 38(4):108-114.)
［7］ZHU X, LEI W, ZHANG S, et al. Image enlargement based on curvature-driven combined with edge-stopping ［J］. Computer Science, 2011, 38(3): 290-291. (祝轩, 雷文娟, 张申华, 等. 曲率驱动与边缘停止相结合的图像放大［J］. 计算机科学, 2011, 38(3): 290-291.)
［8］UDIN L I, OSHER S, FATEMI E. Nonlinear total variation based noise removal algorithms［J］. Physical D: Nonlinear Phenomena, 1992, 60(1): 259-268.
［9］ZHU X, ZHOU M, ZHU C, et al. The Curvature-Driven combined with edge-stopping non-linear diffusion applied in image denoising［J］. Acta Photonica Sinica, 2008, 37(3):609-612. (祝轩, 周明全,朱春香,等. 曲率驱动与边缘停止相结合的非线性扩散及其在图像去噪中的应用［J］. 光子学报, 2008, 37(3):609-612.)
［10］SHI C, WANG Y, LI C, et al. Image enlargement and enhancement methods based on the total variation［J］. Computer Engineering and Applications, 2004, 40(2): 95-98.(石澄贤, 王元全, 李朝峰, 等. 基于总变差的图像放大和增强方法［J］. 计算机工程与应用, 2004, 40(2): 95-98.)
［11］CHAN T F, SHEN J. Non-texture inpainting by Curvature-Driven Diffusions (CDD)［J］. Journal of Visual Communication and Image Representation, 2001, 12(4): 436-449.
［12］SUN J, XU Z, SHUM H Y. Image super-resolution using gradient profile prior［C］// CVPR 2008: IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2008: 1-8.
［13］GONZALEZ R C, WOODS R E. Digital image processing［M］. 3rd ed. RUAN Q, RUAN Z, Translated. Beijing: Publishing House of Electronics Industry, 2011 (冈萨雷斯, 伍兹. 数字图像处理［M］. 3版. 阮秋琦, 阮宇智,等译. 北京: 电子工业出版社, 2011.)
［14］KEYS R. Cubic convolution interpolation for digital image processing［J］. IEEE Transactions on Acoustics, Speech and Signal Processing, 1981, 29(6): 1153-1160.
［15］REICHENBACH S E, GENG F. Two-dimensional cubic convolution［J］. IEEE Transactions on Image Processing, 2003, 12(8): 857-865.
［16］SHI J, REICHENBACH S E. Image interpolation by two-dimensional parametric cubic convolution［J］. IEEE Transactions on Image Processing, 2006, 15(7): 1857-1870.
［17］CHEN M-J, HUANG C-H, LEE W L. A fast edge-oriented algorithm for image interpolation［J］. Image and Vision Computing, 2005, 23(9): 791-798.
［18］ZHU N, WU J, WANG Z. The method of partial differential equations for image enlargement［J］. Journal of Computer-Aided Design and Computer Graphics, 2005, 17(9): 1941-1945. (朱宁, 吴静, 王忠谦. 图像放大的偏微分方程方法［J］. 计算机辅助设计与图形学学报, 2005, 17(9): 1941-1945.)
［19］PERONA P, MALIK J. Scale-space and edge detection using anisotropic diffusion［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1990, 12(7): 629-639.
［20］GLASNER D, BAGON S, IRANI M. Super-resolution from a single image［C］// ICCV 2009: IEEE 12th International Conference on Computer Vision. Piscataway: IEEE, 2009: 349-356.
［21］WANG L. Image enlargement based on partial differential equations［D］. Xi’an: Northwest University, 2009.(王蕾. 基于偏微分方程的图像放大研究［D］.西安: 西北大学, 2009.)
［22］CHEN M J, BOVIK A C. No-reference image blur assessment using multiscale gradient［J］. EURASIP Journal on Image and Video Processing, 2011, 2011(1): 1-11.
［23］SILVA E A, PANETTA K, AGAIAN S S. Quantifying image similarity using measure of enhancement by entropy［C］// SPIE 2007: Proceedings of SPIE 2007. Bellingham: SPIE, 2007:216-227.
［24］HUANG W, CHEN R, ZHANG J. The improvement and implementation for objective measurement methods of digital video image quality［J］. Journal of Beijing University of Posts and Telecommunications, 2005,28(4):87-90. (黄文辉, 陈仁雷, 张家谋. 数字视频图像质量客观测量方法的改进与实现［J］. 北京邮电大学学报, 2005,28(4):87-90.)

[1]	吴军欧阳艾嘉张琳. 基于影响度的统计显著序列模式挖掘算法[J]. 计算机应用, 0, (): 0-0.
[2]	张璐方春祝铭. 基于Res2Net-YOLACT和融合特征的室内跌倒检测算法[J]. 计算机应用, 0, (): 0-0.
[3]	殷雨昌王洪元陈莉冯尊登肖宇. 基于单标注样本的多损失学习与联合度量视频行人重识别[J]. 计算机应用, 0, (): 0-0.
[4]	胡军许正康刘立钟福金张清华. 融合多粒度社区信息的网络嵌入方法[J]. 计算机应用, 0, (): 0-0.
[5]	李润泽孙雪姣. 基于时间条件提取序列的数据流偏好查询[J]. 计算机应用, 0, (): 0-0.
[6]	罗圣钦陈金怡李洪均. 基于注意力机制的多尺度残差UNet实现乳腺癌灶分割[J]. 计算机应用, 0, (): 0-0.
[7]	曹一珉蔡磊高敬阳. 基于生成对抗网络的基因数据生成方法[J]. 计算机应用, 0, (): 0-0.
[8]	陈冲闫珠赵继轩何为梁华庆. 基于集合经验模态分解和长短期记忆网络的催化裂化装置NOx排放预测[J]. 计算机应用, 0, (): 0-0.
[9]	徐光柱林文杰陈莎匡婉雷帮军周军. U-Net与自适应阈值脉冲耦合神经网络相结合的眼底血管分割方法[J]. 计算机应用, 0, (): 0-0.
[10]	杨鼎康黄帅王顺利翟鹏李一丹张立华. 基于对抗生成网络和网络集成的面部表情识别方法EE-GAN[J]. 计算机应用, 0, (): 0-0.
[11]	李讷徐光柱雷帮军马国亮石勇涛. 交通道路行驶车辆车标识别算法[J]. 计算机应用, 0, (): 0-0.
[12]	孟杰王莉杨延杰廉飚. 基于多模态深度融合的虚假信息检测[J]. 计算机应用, 0, (): 0-0.
[13]	秦庭威赵鹏程秦品乐曾建朝柴锐黄永琦. 基于残差注意力机制的点云配准算法[J]. 计算机应用, 0, (): 0-0.
[14]	鲁永帅唐英杰马鑫然. 基于深度特征融合的无纺布低对比度浆丝缺陷检测方法[J]. 计算机应用, 0, (): 0-0.
[15]	王宇航周永霞吴良武. 基于高斯函数的池化算法[J]. 计算机应用, 0, (): 0-0.