Color image classification via quaternion principal component analysis network

The principal component analysis network (PCANet), which is one of the recently proposed deep learning architectures, achieves the state-of-the-art classification accuracy in various datasets and reveals a simple baseline for deep learning networks. However, the performance of PCANet may be degraded when dealing with color images due to the fact that the architecture of PCANet cannot properly utilize the spatial relationship between each color channel in three dimensional color image. In this paper, a quaternion principal component analysis network (QPCANet), which extends PCANet by using quaternion theory, is proposed for color image classification. Compared to PCANet, the proposed QPCANet takes into account the spatial distribution information of RGB channels in color images and ensures larger amount of intra-class invariance by using quaternion domain representation for color images. Experiments conducted on different color image datasets such as UC Merced Land Use, Georgia Tech face, CURet and Caltech-101 have revealed that the proposed QPCANet generally achieves higher classification accuracy than PCANet in color image classification task. The experimental results also verify that QPCANet has much better rotation invariance than PCANet when color image dataset contains lots of rotation information and demonstrate even a simple one-layer QPCANet may obtain satisfactory accuracy when compared with two-layer PCANet.

[1]  Reshma Khemchandani,et al.  Color image classification and retrieval through ternary decision structure based multi-category TWSVM , 2015, Neurocomputing.

[2]  Y-Lan Boureau,et al.  Learning Convolutional Feature Hierarchies for Visual Recognition , 2010, NIPS.

[3]  Kar-Ann Toh,et al.  Face detection based on skin color likelihood , 2014, Pattern Recognit..

[4]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Pietro Perona,et al.  Learning Generative Visual Models from Few Training Examples: An Incremental Bayesian Approach Tested on 101 Object Categories , 2004, 2004 Conference on Computer Vision and Pattern Recognition Workshop.

[6]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[7]  Bin Gu,et al.  A Robust Regularization Path Algorithm for $\nu $ -Support Vector Classification , 2017, IEEE Transactions on Neural Networks and Learning Systems.

[8]  Yanfeng Sun,et al.  Color face recognition based on quaternion matrix representation , 2011, Pattern Recognit. Lett..

[9]  Bin Gu,et al.  Incremental Support Vector Learning for Ordinal Regression , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[10]  Stan Z. Li,et al.  Learning Stacked Image Descriptor for Face Recognition , 2016, IEEE Transactions on Circuits and Systems for Video Technology.

[11]  Yoshua. Bengio,et al.  Learning Deep Architectures for AI , 2007, Found. Trends Mach. Learn..

[12]  Shun'ichi Kaneko,et al.  Robust matching of 3D contours using iterative closest point algorithm improved by M-estimation , 2003, Pattern Recognit..

[13]  Koen E. A. van de Sande,et al.  Evaluating Color Descriptors for Object and Scene Recognition , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  Soo-Chang Pei,et al.  Quaternion matrix singular value decomposition and its applications for color image processing , 2003, Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429).

[15]  Changshui Zhang,et al.  DeepFish: Accurate underwater live fish recognition with a deep architecture , 2016, Neurocomputing.

[16]  Lilong Shi,et al.  Quaternion Color Texture Segmentation , 2006 .

[17]  Eduardo Bayro-Corrochano,et al.  Modeling the 3D kinematics of the eye in the geometric algebra framework , 2003, Pattern Recognit..

[18]  Qiang Guo,et al.  Convolutional feature learning and Hybrid CNN-HMM for scene number recognition , 2016, Neurocomputing.

[19]  Yihong Gong,et al.  Linear spatial pyramid matching using sparse coding for image classification , 2009, CVPR.

[20]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[21]  Stéphane Mallat,et al.  Group Invariant Scattering , 2011, ArXiv.

[22]  R. Mooney,et al.  Impact of Similarity Measures on Web-page Clustering , 2000 .

[23]  Stefanos Zafeiriou,et al.  Full-Angle Quaternions for Robustly Matching Vectors of 3D Rotations , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[24]  Christine Fernandez-Maloigne,et al.  Spatial and spectral quaternionic approaches for colour images , 2007, Comput. Vis. Image Underst..

[25]  Wen Gao,et al.  Multilevel Modified Finite Radon Transform Network for Image Upsampling , 2016, IEEE Transactions on Circuits and Systems for Video Technology.

[26]  Chu He,et al.  A deep graph embedding network model for face recognition , 2014, 2014 12th International Conference on Signal Processing (ICSP).

[27]  Stéphane Mallat,et al.  Invariant Scattering Convolution Networks , 2012, IEEE transactions on pattern analysis and machine intelligence.

[28]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[29]  Jun Guo,et al.  An empirical convolutional neural network approach for semantic relation classification , 2016, Neurocomputing.

[30]  David J. Field,et al.  Emergence of simple-cell receptive field properties by learning a sparse code for natural images , 1996, Nature.

[31]  Lawrence D. Jackel,et al.  Backpropagation Applied to Handwritten Zip Code Recognition , 1989, Neural Computation.

[32]  Jiasong Wu,et al.  Quaternion Bessel-Fourier moments and their invariant descriptors for object reconstruction and recognition , 2014, Pattern Recognit..

[33]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[34]  Vipin Kumar,et al.  Finding Clusters of Different Sizes, Shapes, and Densities in Noisy, High Dimensional Data , 2003, SDM.

[35]  Bin Yu,et al.  Feature learning based on SAE-PCA network for human gesture recognition in RGBD images , 2015, Neurocomputing.

[36]  Anant Madabhushi,et al.  A Deep Convolutional Neural Network for segmenting and classifying epithelial and stromal regions in histopathological images , 2016, Neurocomputing.

[37]  Richard G. Baraniuk,et al.  Coherent Multiscale Image Processing Using Dual-Tree Quaternion Wavelets , 2008, IEEE Transactions on Image Processing.

[38]  Honglak Lee,et al.  Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations , 2009, ICML '09.

[39]  Yihong Gong,et al.  Nonlinear Learning using Local Coordinate Coding , 2009, NIPS.

[40]  Matti Pietikäinen,et al.  Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[41]  Ming Zhu,et al.  Quaternion Fourier-Mellin moments for color images , 2011, Pattern Recognit..

[42]  Xiang Zhang,et al.  OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks , 2013, ICLR.

[43]  Anil K. Jain,et al.  Object detection using gabor filters , 1997, Pattern Recognit..

[44]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[45]  Jiwen Lu,et al.  PCANet: A Simple Deep Learning Baseline for Image Classification? , 2014, IEEE Transactions on Image Processing.

[46]  Geoffrey E. Hinton,et al.  Deep Boltzmann Machines , 2009, AISTATS.

[47]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[48]  Geoffrey E. Hinton,et al.  Autoencoders, Minimum Description Length and Helmholtz Free Energy , 1993, NIPS.

[49]  Michael S. Lew,et al.  Deep learning for visual understanding: A review , 2016, Neurocomputing.

[50]  Jack B. Kuipers,et al.  Quaternions and Rotation Sequences: A Primer with Applications to Orbits, Aerospace and Virtual Reality , 2002 .

[51]  A. S. Solodovnikov,et al.  Hypercomplex Numbers: An Elementary Introduction to Algebras , 1989 .

[52]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[53]  Pascal Vincent,et al.  Representation Learning: A Review and New Perspectives , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[54]  Ling Shao,et al.  A rapid learning algorithm for vehicle classification , 2015, Inf. Sci..

[55]  Nicolas Le Bihan,et al.  Quaternion principal component analysis of color images , 2003, Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429).

[56]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[57]  Thomas G. Dietterich.  What is machine learning? , 2020, Archives of Disease in Childhood.

[58]  Yuhui Zheng,et al.  Image segmentation by generalized hierarchical fuzzy C-means algorithm , 2015, J. Intell. Fuzzy Syst..

[59]  Shree K. Nayar,et al.  Reflectance and texture of real-world surfaces , 1999, TOGS.

[60]  Zhao Zhang,et al.  Simple yet effective color principal and discriminant feature extraction for representing and recognizing color images , 2015, Neurocomputing.

[61]  Dennis Gabor,et al.  Theory of communication , 1946 .

[62]  André Ricardo Backes,et al.  Color texture classification based on gravitational collapse , 2013, Pattern Recognit..

[63]  Shenghuo Zhu,et al.  Deep Coding Network , 2010, NIPS.

[64]  P. Cochat,et al.  Et al , 2008, Archives de pediatrie : organe officiel de la Societe francaise de pediatrie.

[65]  Stéphane Mallat,et al.  Rotation, Scaling and Deformation Invariant Scattering for Texture Discrimination , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[66]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[67]  David G. Lowe,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004, International Journal of Computer Vision.

[68]  Stephen J. Sangwine,et al.  Hypercomplex Fourier Transforms of Color Images , 2001, IEEE Transactions on Image Processing.

[69]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[70]  Lianwen Jin,et al.  DLANet: A manifold-learning-based discriminative feature learning network for scene classification , 2015, Neurocomputing.

[71]  Yoshua Bengio,et al.  Maxout Networks , 2013, ICML.

[72]  Chih-Jen Lin,et al.  LIBLINEAR: A Library for Large Linear Classification , 2008, J. Mach. Learn. Res..

[73]  Fuzhen Zhang.  Quaternions and matrices of quaternions , 1997 .

[74]  Liming Chen,et al.  Image region description using orthogonal combination of local binary patterns enhanced with color information , 2013, Pattern Recognit..

[75]  D. Gabor,et al.  Theory of communication. Part 1: The analysis of information , 1946 .

[76]  Ming Dai,et al.  Multifocus color image fusion based on quaternion curvelet transform. , 2012, Optics express.

[77]  Shan Gai,et al.  New banknote defect detection algorithm using quaternion wavelet transform , 2016, Neurocomputing.

[78]  Xinbo Gao,et al.  2DPCANet: Dayside Aurora Classification Based on Deep Learning , 2015, CCCV.

[79]  Shawn D. Newsam,et al.  Bag-of-visual-words and spatial extensions for land-use classification , 2010, GIS '10.

[80]  Gang Chen,et al.  Color Image Analysis by Quaternion-Type Moments , 2014, Journal of Mathematical Imaging and Vision.

[81]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[82]  Gregory Shakhnarovich,et al.  Face Recognition in Subspaces , 2011, Handbook of Face Recognition.

[83]  Yann LeCun,et al.  What is the best multi-stage architecture for object recognition? , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[84]  Jiasong Wu,et al.  Tensor object classification via multilinear discriminant analysis network , 2014, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).