Multi-Frame Super-Resolution Reconstruction Based on Gradient Vector Flow Hybrid Field

被引:18
作者
Huang, Shuying [1 ]
Sun, Jun [1 ]
Yang, Yong [2 ]
Fang, Yuming [2 ]
Lin, Pan [3 ]
机构
[1] Jiangxi Univ Finance & Econ, Sch Software & Commun Engn, Nanchang 330032, Jiangxi, Peoples R China
[2] Jiangxi Univ Finance & Econ, Sch Informat Technol, Nanchang 330032, Jiangxi, Peoples R China
[3] Xi An Jiao Tong Univ, Inst Biomed Engn, Xian 710049, Peoples R China
来源
IEEE ACCESS | 2017年 / 5卷
基金
中国国家自然科学基金;
关键词
Super-resolution; gradient vector flow; shock filter; image enhancement; regularization; IMAGE SUPERRESOLUTION; SPARSE; ENHANCEMENT;
D O I
10.1109/ACCESS.2017.2757239
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
In this paper, we propose a novel multi-frame super-resolution (SR) method, which is developed by considering image enhancement and denoising into the SR processing. For image enhancement, a gradient vector flow hybrid field (GVFHF) algorithm, which is robust to noise is first designed to capture the image edges more accurately. Then, through replacing the gradient of anisotropic diffusion shock filter (ADSF) by GVFHF, a GVFHF-based ADSF (GVFHF-ADSF) model is proposed, which can effectively achieve image denoising and enhancement. In addition, a difference curvature-based spatial weight factor is defined in the GVFHF-ADSF model to obtain an adaptive weight between denoising and enhancement in the flat and edge regions. Finally, a GVFHF-ADSF-based multi-frame SR method is presented by employing the GVFHF-ADSF model as a regularization term and the steepest descent algorithm is adopted to solve the inverse SR problem. Experimental results and comparisons with existing methods demonstrate that the proposed GVFHF-ADSF-based SR algorithm can effectively suppress both Gaussian and salt-and-pepper noise, meanwhile enhance edges of the reconstructed image.
引用
收藏
页码:21669 / 21683
页数:15
相关论文
共 43 条
[1]   SIGNAL AND IMAGE-RESTORATION USING SHOCK FILTERS AND ANISOTROPIC DIFFUSION [J].
ALVAREZ, L ;
MAZORRA, L .
SIAM JOURNAL ON NUMERICAL ANALYSIS, 1994, 31 (02) :590-605
[2]   Adaptive total variation denoising based on difference curvature [J].
Chen, Qiang ;
Montesinos, Philippe ;
Sen Sun, Quan ;
Heng, Peng Ann ;
Xia, De Shen .
IMAGE AND VISION COMPUTING, 2010, 28 (03) :298-306
[3]   A New Single Image Super-Resolution Method Based on the Infinite Mixture Model [J].
Cheng, Peitao ;
Qiu, Yuanying ;
Wang, Xiumei ;
Zhao, Ke .
IEEE ACCESS, 2017, 5 :2228-2240
[4]  
Demirel Hasan, 2009, 2009 17th European Signal Processing Conference (EUSIPCO 2009), P1097
[5]   Similarity Constraints-Based Structured Output Regression Machine: An Approach to Image Super-Resolution [J].
Deng, Cheng ;
Xu, Jie ;
Zhang, Kaibing ;
Tao, Dacheng ;
Gao, Xinbo ;
Li, Xuelong .
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2016, 27 (12) :2472-2485
[6]   Accelerating the Super-Resolution Convolutional Neural Network [J].
Dong, Chao ;
Loy, Chen Change ;
Tang, Xiaoou .
COMPUTER VISION - ECCV 2016, PT II, 2016, 9906 :391-407
[7]   A new denoising model for multi-frame super-resolution image reconstruction [J].
El Mourabit, Idriss ;
El Rhabi, Mohammed ;
Hakim, Abdelilah ;
Laghrib, Amine ;
Moreau, Eric .
SIGNAL PROCESSING, 2017, 132 :51-65
[8]   Fast and robust multiframe super resolution [J].
Farsiu, S ;
Robinson, MD ;
Elad, M ;
Milanfar, P .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2004, 13 (10) :1327-1344
[9]   Image enhancement and denoising by complex diffusion processes [J].
Gilboa, G ;
Sochen, N ;
Zeevi, YY .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2004, 26 (08) :1020-1036
[10]   Single Image Super-Resolution via Locally Regularized Anchored Neighborhood Regression and Nonlocal Means [J].
Jiang, Junjun ;
Ma, Xiang ;
Chen, Chen ;
Lu, Tao ;
Wang, Zhongyuan ;
Ma, Jiayi .
IEEE TRANSACTIONS ON MULTIMEDIA, 2017, 19 (01) :15-26