基于LRC-SNN的图像高效重建与识别

doi:10.19678/j.issn.1000-3428.0055065

摘要/Abstract

摘要： 图像集分类算法种类较多，但多数存在运算繁琐、计算成本高和时效性差的问题。为此，提出一种改进的图像重建与识别算法，利用线性回归分类和共享最近邻子空间分类理论进行图像重建和分类，通过将图像下采样建立的高维空间重建为子空间，避免计算复杂度较高的训练过程。利用各个类别的图像集子空间对测试图像进行回归模型估计，根据回归模型重建测试集中的图像，基于重建图像和原始图像间重建误差最小化法，采用加权投票策略对测试集进行估计以确定图像所属的类别。在UCSD/Honda、CMU、ETH-8和YouTube数据集上进行实验，结果表明，在低分辨率采样条件下，与ADNT算法相比，该算法平均分类精度提高3.6%，运算效率提高10倍，其最快响应时间缩短至2.8 ms。

关键词: 图像集分类, LRC-SNN回归模型, 误差最小化, 加权投票策略, 分类精度, 计算速度

Abstract: Most of existing classification methods for image sets are costly,having high computational complexity and poor timeliness.To address the problem,this paper proposes an improved image reconstruction and recognition algorithm.The algorithm uses the Linear Regression Classification(LRC) and Share Nearest Neighbor(SNN) subspace classification theory for image reconstruction and classification.The high-dimensional space built by image subsampling is taken as subspace to avoid the training process with high computational complexity.Then,subspace of different categories of image sets is used to implement regression model estimation for test images.For images in the test set of regression model reconstruction,their categories are determined by using the weighted voting strategy to estimate the test set under the principle that the errors between reconstructed images and original images should be minimized.Experimental results on UCSD/Honda,CMU,ETH-8 and YouTube datasets show that under low-resolution sampling conditions,compared with the ADNT algorithm,the proposed algorithm increases the average classification accuracy by 3.6%,computational efficiency by 10 times,and shortens the fastest response time to 2.8 ms.

Key words: image set classification, LRC-SNN regression model, error minimization, weighted voting strategy, classification accuracy, computational speed

中图分类号:

TP393

索静, 宋林林, 李强. 基于LRC-SNN的图像高效重建与识别[J]. 计算机工程, 2020, 46(7): 243-250,259.

SUO Jing, SONG Linlin, LI Qiang. Efficient Image Reconstruction and Recognition Based on LRC-SNN[J]. Computer Engineering, 2020, 46(7): 243-250,259.

https://www.ecice06.com/CN/Y2020/V46/I7/243

参考文献

[1] LÜ Wei,WANG Zhicheng,ZHAO Weidong,et al.An image set classification method based on low rank description[J].Journal of Tongji University(Natural Science),2013,41(2):271-276.(in Chinese) 吕煊,王志成,赵卫东,等.一种基于低秩描述的图像集分类方法[J].同济大学学报(自然科学版),2013,41(2):271-276.
[2] HAYAT M,BENNAMOUN M,AN S J.Deep recon-struction models for image set classification[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(4):713-727.
[3] WANG Bin,HUANG Zhuqin,CHEN Liangxiao.Circular features description:effective method for leaf image retrieval and classification[J].Journal of Software,2019,30(4):1148-1163.(in Chinese) 王斌,黄竹芹,陈良宵.圆周特征描述:有效的叶片图像分类和检索方法[J].软件学报,2019,30(4):1148-1163.
[4] BAI Cong,HUANG Ling,CHEN Jianan,et al.Optimization of deep convolutional neural network for large scale image classification[J].Journal of Software,2018,29(4):1029-1038.(in Chinese) 白琮,黄玲,陈佳楠,等.面向大规模图像分类的深度卷积神经网络优化[J].软件学报,2018,29(4):1029-1038.
[5] GUI Jiangsheng,MA Chenfei,BAO Xiaoan,et al.Fine-grained image classification method for recurrent deep hybrid attention network[J].Computer Engineering,2019,45(5):205-209.(in Chinese) 桂江生,麻陈飞,包晓安,等.递归深度混合关注网络的细粒度图像分类方法[J].计算机工程,2019,45(5):205-209.
[6] XIE Yonghua,ZHU Yangang,ZHAO Xianguo.Classification and identification of pollen images based on Zernike moment and BoF-SURF feature fusion[J].Computer Engineering,2018,44(7):259-263,270.(in Chinese) 谢永华,朱延刚,赵贤国.基于Zernike矩与BoF-SURF特征融合的花粉图像分类识别[J].计算机工程,2018,44(7):259-263,270.
[7] ZHANG Shun,GONG Yihong,WANG Jinjun.The development of deep convolution neural network and its applications on computer vision[J].Chinese Journal of Computers,2019,42(3):453-482.(in Chinese) 张顺,龚怡宏,王进军.深度卷积神经网络的发展及其在计算机视觉领域的应用[J].计算机学报,2019,42(3):453-482.
[8] LU J W,WANG G,ZHOU J.Simultaneous feature and dictionary learning for image set based face recognition[J].IEEE Transactions on Image Processing,2017,26(8):4042-4054.
[9] HUANG Z W,WANG R P,SHAN S G,et al.Face recognition on large-scale video in the wild with hybrid Euclidean-and-Riemannian metric learning[J].Pattern Recognition,2015,48(10):3113-3124.
[10] HU Y Q,MIAN A S,OWENS R.Face recognition using sparse approximated nearest points between image sets[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(10):1992-2004.
[11] KIM T K,KITTLER J,CIPOLLA R.Discriminative learning and recognition of image set classes using canonical correlations[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2007,29(6):1005-1018.
[12] HUANG Z W,WANG R P,SHAN S G,et al.Projection metric learning on Grassmann manifold with application to video based face recognition[C]//Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2015:140-149.
[13] FENG J,WANG J,ZHANG H G,et al.Fault diagnosis method of joint fisher discriminant analysis based on the local and global manifold learning and its kernel version[J].IEEE Transactions on Automation Science and Engineering,2016,13(1):122-133.
[14] LU J W,WANG G,MOULIN P.Localized multifeature metric learning for image-set-based face recognition[J].IEEE Transactions on Circuits and Systems for Video Technology,2016,26(3):529-540.
[15] HARANDI M T,SANDERSON C,SHIRAZI S,et al.Graph embedding discriminant analysis on Grassmannian manifolds for improved image set matching[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2011:2705-2712.
[16] HU Y Q,MIAN A S,OWENS R.Face recognition using sparse approximated nearest points between image sets[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(10):1992-2004.
[17] WANG R P,GUO H M,DAVIS L S,et al.Covariance discriminative learning:a natural and efficient approach to image set classification[C]//Proceedings of 2012 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2012:2496-2503.
[18] YANG M,ZHU P,GOOL L V,et al.Face recognition based on regularized nearest points between image sets[C]//Proceedings of IEEE International Conference and Workshops on Automatic Face and Gesture Recognition.Washington D.C.,USA:IEEE Computer Society,2017:1-7.
[19] ORTIZ E G,WRIGHT A,SHAH M.Face recognition in movie trailers via mean sequence sparse representation-based classification[C]//Proceedings of 2013 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2013:3531-3538.
[20] ZHU P F,ZHANG L,ZUO W M,et al.From point to set:extend the learning of distance metrics[C]//Proceedings of 2013 IEEE International Conference on Computer Vision.Washington D.C.,USA:IEEE Press,2013:2664-2671.
[21] CHEN L.Dual linear regression based classification for face cluster recognition[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2015:2673-2680.
[22] FENG Q X,ZHOU Y C,LAN R S.Pairwise linear regression classification for image set retrieval[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2016:4865-4872.
[23] HAYAT M,BENNAMOUN M,AN S J.Learning non-linear reconstruction models for image set classification[C]//Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2014:1915-1922.
[24] HAYAT M,BENNAMOUN M,AN S.Deep reconstruction models for image set classification[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(4):713-727.
[25] SHORE A,HARTMANN W M.Improvements in transaural synthesis with the Moore-Penrose pseudoinverse matrix[J].The Journal of the Acoustical Society of America,2018,143(3):1938-1940.
[26] CHIRANJEEVI P,GOPALAKRISHNAN V,MOOGI P.Neutral face classification using personalized appearance models for fast and robust emotion detection[J].IEEE Transactions on Image Processing,2015,24(9):2701-2711.
[27] VIOLA P,JONES M J.Robust real-time face detection[J].International Journal of Computer Vision,2004,57:137-154.

选择文件类型/文献管理软件名称

选择包含的内容