[1]刘丹霞,干宗良,杨文峰. 基于相似性约束的人脸超分辨率重建算法[J].计算机技术与发展,2015,25(08):58-61.
　LIU Dan-xia,GAN Zong-liang,YANG Wen-feng. A Face Super-resolution Reconstruction Algorithm Based on Similarity Constraints[J].,2015,25(08):58-61.
点击复制

 基于相似性约束的人脸超分辨率重建算法()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
25
期数:
2015年08期
页码:
58-61
栏目:
智能、算法、系统工程
出版日期:
2015-08-10

文章信息/Info

Title:
 A Face Super-resolution Reconstruction Algorithm Based on Similarity Constraints
文章编号:
1673-629X（2015)08-0058-04
作者:
 刘丹霞; 干宗良; 杨文峰
 南京邮电大学 图像处理与图像通信江苏省重点实验室
Author(s):
 LIU Dan-xia; GAN Zong-liang; YANG Wen-feng
关键词:
 ; 迭代; 相似性约束; 流形学习; 人脸重建
Keywords:
 ; iteration; similarity constraints; manifold learning; face reconstruction
分类号:
TP301.6
文献标志码:
A
摘要:
 提出一种改进的基于相似性约束的人脸超分辨率重建算法，采用迭代计算的方式将训练过程和学习过程整合在一起。首先从训练集中遴选出与待重建人脸最相似的训练库人脸参与迭代过程，随着迭代次数的增加，重建得到的高分辨率人脸越来越接近于原始高分辨率人脸；其中每次迭代分别统计待重建低分辨率人脸和训练集本次迭代参与的低分辨率人脸的相似性以及与训练集本次迭代参与的高分辨率人脸在局部结构上的相似性，以减少流形学习中低维空间到高维空间的一对多映射的限制。实验结果表明，与其他算法相比，文中所提的人脸重建算法不仅具有较低的空间复杂度，并且具有更好的主观和客观效果。
Abstract:
 An improved face Super-Resolution ( SR) reconstruction algorithm based on similarity constraints is proposed. The proposed algorithm incorporates training stage and learning stage together. Select the most similar face sets ( low resolution faces and corresponding high resolution faces) from the whole training face sets with the input Low Resolution ( LR) face. With the increasing of iterative num-bers,the reconstruction result gets more and more close to the original High Resolution (HR) face. During each iterative learing,the simi-larity between the input LR face image and the training LR face image is computed as well as the local structure similarity between the in-put LR face and the training HR face. The experimental results demonstrate that the proposed algorithm not only occupies less space com-plexity but also produces better subjective and objective results compared with other leading super-resolution reconstruction algorithms.

相似文献/References:

[1]胡为成[] 王本年 程转流[].基于RUP思想和B／S模式的考试系统[J].计算机技术与发展,2006,(03):137.
　HU Wei-cheng,WANG Ben-nian,CHENG Zhuan-liu.A Test System Based on Idea of RUP and B/S Mode[J].,2006,(08):137.
[2]张国生.涉众为中心的敏捷需求建模[J].计算机技术与发展,2012,(02):33.
　ZHANG Guo-sheng.Stakeholder-Centered Agile Requirements Modeling[J].,2012,(08):33.
[3]刘颖 刘健波.幻方群在图像置乱中的研究与应用[J].计算机技术与发展,2012,(09):119.
　LIU Ying,LIU Jian-bo.Study and Application of Magic Square Group in Process of Image Scrambling[J].,2012,(08):119.
[4]张志宏,吴庆波,邵立松,等.基于飞腾平台TOE协议栈的设计与实现[J].计算机技术与发展,2014,24(07):1.
　ZHANG Zhi-hong,WU Qing-bo,SHAO Li-song,et al. Design and Implementation of TCP/IP Offload Engine Protocol Stack Based on FT Platform[J].,2014,24(08):1.
[5]梁文快,李毅. 改进的基因表达算法对航班优化排序问题研究[J].计算机技术与发展,2014,24(07):5.
　LIANG Wen-kuai,LI Yi. Research on Optimization of Flight Scheduling Problem Based on Improved Gene Expression Algorithm[J].,2014,24(08):5.
[6]黄静,王枫,谢志新,等. EAST文档管理系统的设计与实现[J].计算机技术与发展,2014,24(07):13.
　HUANG Jing,WANG Feng,XIE Zhi-xin,et al. Design and Implementation of EAST Document Management System[J].,2014,24(08):13.
[7]侯善江[],张代远[][][]. 基于样条权函数神经网络P2P流量识别方法[J].计算机技术与发展,2014,24(07):21.
　HOU Shan-jiang[],ZHANG Dai-yuan[][][]. P2P Traffic Identification Based on Spline Weight Function Neural Network[J].,2014,24(08):21.
[8]李璨,耿国华,李康,等. 一种基于三维模型的文物碎片线图生成方法[J].计算机技术与发展,2014,24(07):25.
　LI Can,GENG Guo-hua,LI Kang,et al. A Method of Obtaining Cultural Debris’ s Line Chart Based on Three-dimensional Model[J].,2014,24(08):25.
[9]翁鹤,皮德常. 混沌RBF神经网络异常检测算法[J].计算机技术与发展,2014,24(07):29.
　WENG He,PI De-chang. Chaotic RBF Neural Network Anomaly Detection Algorithm[J].,2014,24(08):29.
[10]刘茜[],荆晓远[],李文倩[],等. 基于流形学习的正交稀疏保留投影[J].计算机技术与发展,2014,24(07):34.
　LIU Qian[],JING Xiao-yuan[,LI Wen-qian[],et al. Orthogonal Sparsity Preserving Projections Based on Manifold Learning[J].,2014,24(08):34.
[11]王晓军,邹亮亮. Hadoop迭代优化技术的研究[J].计算机技术与发展,2014,24(09):98.
　WANG Xiao-jun,ZOU Liang-liang. Research on Optimizing Iterative Technology of Hadoop[J].,2014,24(08):98.

更新日期/Last Update: 2015-09-11