Numerical solutions to regularized face hallucination

Computer Engineering and Applications ›› 2011, Vol. 47 ›› Issue (36): 215-218.

• 图形、图像、模式识别 • Previous Articles Next Articles

Numerical solutions to regularized face hallucination

JIANG Jing1，2，ZHANG Xuesong3

1.Department of Mechanical and Electrical Engineering，North China Institute of Science and Technology，Beijing 101601，China
2.State Key Lab of Coal Resources and Safe Mining，China University of Mining and Technology（Beijing），Beijing 100083，China
3.Electro-optical Information Security Control Laboratory，The 53rd Institute，CETC，Sanhe，Hebei 065201，China

Received:1900-01-01 Revised:1900-01-01 Online:2011-12-21 Published:2011-12-21

规整化人脸图像超分辨率重建的数值解法

江静1，2，张雪松3

1.华北科技学院机电工程系，北京 101601
2.中国矿业大学（北京）煤炭资源与安全开采国家重点实验室，北京 100083
3.中国电子科技集团第53研究所光电信息控制和安全技术重点实验室，河北三河 065201

Abstract

Abstract: This paper proposes an eigen-subspace based regularization method for face image Super-Resolution Reconstruction（SRR），and presents three numerical solutions to the SRR problem.Under the affine motion model，it extends the interpolation of image using the four-neighbor interpolation to the estimation of image gradient field，and derives the Jacobian of the High Resolution（HR） image with respect to the motion parameters.By means of the total and partial differential expansions of the SRR cost functional，it reduces the nonlinear SRR problem to a linear problem and presents three iterative algorithms for the joint estimation of motion parameters and HR image.An adaptive calculation method for the SRR regularization parameter is proposed to fulfill the automatic SRR of facial imagery.Simulation results verify the superiority of the proposed face sub-space regularized method over the traditional regularization methods（Laplacian and Total Variation（TV）） and demonstrate good face image SRR performance even in the case of low signal to noise ratio.

Key words: super-resolution reconstruction, face images, adaptive regularization, numerical solutions

摘要： 提出了基于特征子空间规整化的人脸图像超分辨率重建（SRR）算法并给出了三种数值解法。在仿射变换运动模型下，将图像的四邻域插值方法拓展为图像的梯度场估计问题，推导出了待求高分辨率（HR）图像关于运动参数的雅科比矩阵;并根据对SRR代价函数的全微分和偏微分展开，将非线性的SRR问题转换为线性问题迭代求解，讨论了三种运动参数与HR图像的联合迭代估计算法。给出了SRR规整化参数的自适应计算方法以实现自动SRR。仿真结果证实：采用的人脸子空间规整化方法优于传统规整化方法（拉普拉斯、全变差），尤其在低信噪比时可以获得良好的人脸图像SRR效果。

关键词: 超分辨率重建, 人脸图像, 自适应规整化, 数值解法

JIANG Jing1，2，ZHANG Xuesong3. Numerical solutions to regularized face hallucination[J]. Computer Engineering and Applications, 2011, 47(36): 215-218.

江静1，2，张雪松3. 规整化人脸图像超分辨率重建的数值解法[J]. 计算机工程与应用, 2011, 47(36): 215-218.

[1]	LI Xianguo, FENG Xinxin, LI Jianxiong. Sigle Image Super-Resolution Reconstruction Based on Multi-scale Residual Network [J]. Computer Engineering and Applications, 2021, 57(7): 215-221.
[2]	LIU Jing, SONG Haichuan, HUANG Jianshe, MA Lizhuang. Channel and Spatial Attention Image Super Resolution Network [J]. Computer Engineering and Applications, 2021, 57(2): 209-216.
[3]	HUANG Jian, ZHAO Yuanyuan, GUO Ping, WANG Jing. Survey of Single Image Super-Resolution Based on Deep Learning [J]. Computer Engineering and Applications, 2021, 57(18): 13-23.
[4]	SUN Jingyang, CHEN Fengdong, HAN Yueyue, WU Yuwen, GAN Yu, LIU Guodong. Overview of Image Super-Resolution Algorithms [J]. Computer Engineering and Applications, 2021, 57(17): 1-9.
[5]	CHEN Guihui, CHEN Wu, LI Zhongbing, YI Xin, LIU Huikang, HAN Chunyang. Image Super Resolution Reconstruction Based on Residual Convolution Attention Network [J]. Computer Engineering and Applications, 2021, 57(12): 193-200.
[6]	CHEN Chen, LIU Mingming, LIU Bing, ZHOU Yong. Image Super-Resolution Reconstruction Algorithm Based on Residual Network [J]. Computer Engineering and Applications, 2020, 56(8): 185-191.
[7]	LI Cheng, ZHANG Yu, HUANG Chuhua. Improved Super-Resolution Reconstruction of Image Based on Generative Adversarial Networks [J]. Computer Engineering and Applications, 2020, 56(4): 191-196.
[8]	ZHANG Kaibing, ZHU Danni, WANG Zhen, YAN Yadi. Survey of Super-Resolution Images Quality Assessment [J]. Computer Engineering and Applications, 2019, 55(4): 31-40.
[9]	WANG Aili1, SONG Xiaoying1, CHEN Yushi2. Super-Resolution Reconstruction of Remote Sensing Image Based on Recursive Residual Network [J]. Computer Engineering and Applications, 2019, 55(3): 191-195.
[10]	ZENG Jiexian, NI Shenlong. Improved Super-Resolution Reconstruction of Single Image Based on Convolution Neural Network [J]. Computer Engineering and Applications, 2019, 55(13): 1-7.
[11]	ZHANG Wei, XU Aiqiang. Application of MKL model incorporated within-class scatter in analog circuit diagnosis [J]. Computer Engineering and Applications, 2018, 54(9): 5-12.
[12]	WANG Xue1, SUI Lichun1, 2, YANG Zhenyin3, KANG Junmei1. Super-resolution reconstruction algorithm of remote sensing images based on method of optimal directions to coupled dictionary learning [J]. Computer Engineering and Applications, 2018, 54(7): 201-205.
[13]	XING Xiaoyang1，2, WEI Min1，2, FU Ying1，2. Super-resolution reconstruction of medical images using feature-based loss [J]. Computer Engineering and Applications, 2018, 54(20): 202-207.
[14]	YU Kanglong1, QIN Weicheng1, YANG Jin1, XU Ruofei2. Image quality assessment method for super-resolution reconstruction image [J]. Computer Engineering and Applications, 2017, 53(2): 201-205.
[15]	CHEN Jin1，2, ZHANG Yu1，2. Multi-phase similarity based super-resolution reconstruction for lung 4D-CT [J]. Computer Engineering and Applications, 2017, 53(15): 191-195.

Numerical solutions to regularized face hallucination

规整化人脸图像超分辨率重建的数值解法

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics