Impact of reduction in descriptor size on object detection and classification

Extraction of distinctive and robust features in image/video analysis and processing has attracted the attention of researchers in the recent years. Elimination of irrelevant and less important features reduces the computational complexity to a great extent at the cost of a very marginal reduction in accuracy. This paper presents a framework for dimensionality reduction of the binary features to obtain a low dimension feature vector for object detection. The process of identification and selection of the most relevant feature is performed in three steps: extraction of features using binary descriptors; Selection of best feature subset using Sequential Forward Selection (SFS) and Principal Component Analysis; classification using SVM classifier. The experimental results show that BRISK and LATCH descriptors perform better even when the dimensionality is reduced from 256, 128, and 64 to 32 bits with an acceptable classification accuracy and significant reduction in run time. However, there is slight decrease in the classification accuracy of LBP, FREAK, BRIEF, and ORB. A classification rate of 84.93% is obtained with LATCH descriptor for a descriptor size of 32 bits.

[1]  Ali Ghodsi,et al.  Dimensionality Reduction A Short Tutorial , 2006 .

[2]  Amit Prakash Singh,et al.  An empirical evaluation of translational and rotational invariance of descriptors and the classification of flower dataset , 2018, Pattern Analysis and Applications.

[3]  A. Izenman.  Linear Discriminant Analysis , 2013 .

[4]  Alan Julian Izenman,et al.  Modern Multivariate Statistical Techniques , 2008 .

[5]  J. Tenenbaum,et al.  A global geometric framework for nonlinear dimensionality reduction. , 2000, Science.

[6]  Georgios Paliouras,et al.  The Effect of Dimensionality Reduction on Large Scale Hierarchical Classification , 2014, CLEF.

[7]  Ravinder Kumar,et al.  A Robust Fingerprint Matching System Using Orientation Features , 2016, J. Inf. Process. Syst..

[8]  Frank Plastria,et al.  Dimensionality Reduction for Classification , 2008, ADMA.

[9]  Bernhard Schölkopf,et al.  Kernel Principal Component Analysis , 1997, ICANN.

[10]  Philippe C. Besse,et al.  A L 1-norm PCA and a Heuristic Approach , 1996 .

[11]  Takeo Kanade,et al.  Robust L/sub 1/ norm factorization in the presence of outliers and missing data by alternative convex programming , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[12]  Joshua B. Tenenbaum,et al.  Global Versus Local Methods in Nonlinear Dimensionality Reduction , 2002, NIPS.

[13]  S T Roweis,et al.  Nonlinear dimensionality reduction by locally linear embedding. , 2000, Science.

[14]  Jonathon Shlens,et al.  A Tutorial on Principal Component Analysis , 2014, ArXiv.

[15]  Miao Sun,et al.  A Classification Leveraged Object Detector , 2016, ArXiv.

[16]  Lubo Popel,et al.  Combining the Principal Components Method with Di erent Learning Algorithms , 2000 .

[17]  Jing Zhang,et al.  Salient object detection and classification for stereoscopic images , 2014, Multimedia Tools and Applications.

[18]  Madasu Hanmandlu,et al.  Rotational invariant fingerprint matching using local directional descriptors , 2014, Int. J. Comput. Intell. Stud..

[19]  Bill Triggs,et al.  Feature Sets and Dimensionality Reduction for Visual Object Detection , 2010, BMVC.

[20]  M. Kristan,et al.  Efficient Dimensionality Reduction Using Random Projection , 2010 .

[21]  Vincent Lepetit,et al.  BRIEF: Binary Robust Independent Elementary Features , 2010, ECCV.

[22]  Ravinder Kumar,et al.  An empirical evaluation of rotation invariance of LDP feature for fingerprint matching using neural networks , 2014, Int. J. Comput. Vis. Robotics.

[23]  Daphne Koller,et al.  Toward Optimal Feature Selection , 1996, ICML.

[24]  Huimin Lu,et al.  Multiple Sclerosis Detection Based on Biorthogonal Wavelet Transform, RBF Kernel Principal Component Analysis, and Logistic Regression , 2016, IEEE Access.

[25]  Ming Yang,et al.  Sensorineural hearing loss detection via discrete wavelet transform and principal component analysis combined with generalized eigenvalue proximal support vector machine and Tikhonov regularization , 2018, Multimedia Tools and Applications.

[26]  Shuicheng Yan,et al.  Neighborhood preserving embedding , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[27]  Matti Pietikäinen,et al.  Computer Vision Using Local Binary Patterns , 2011, Computational Imaging and Vision.

[28]  Pierre Vandergheynst,et al.  FREAK: Fast Retina Keypoint , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[29]  Ruxandra Tapu,et al.  A computer vision-based perception system for visually impaired , 2017, Multimedia Tools and Applications.

[30]  Anjan Gudigar,et al.  A review on automatic detection and recognition of traffic sign , 2014, Multimedia Tools and Applications.

[31]  Michael G. Madden,et al.  The Effect of Principal Component Analysis on Machine Learning Accuracy with High Dimensional Spectral Data , 2005, SGAI Conf..

[32]  Pat Langley,et al.  Selection of Relevant Features and Examples in Machine Learning , 1997, Artif. Intell..

[33]  Ann B. Lee,et al.  Diffusion maps and coarse-graining: a unified framework for dimensionality reduction, graph partitioning, and data set parameterization , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[34]  Stefan Hinz,et al.  Investigation of the impact of dimensionality reduction and feature selection on the classification of hyperspectral EnMAP data , 2016, 2016 8th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS).

[35]  Anil K. Jain,et al.  Feature Selection: Evaluation, Application, and Small Sample Performance , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[36]  Tom Drummond,et al.  Machine Learning for High-Speed Corner Detection , 2006, ECCV.

[37]  Roland Siegwart,et al.  BRISK: Binary Robust invariant scalable keypoints , 2011, 2011 International Conference on Computer Vision.

[38]  I. Jolliffe.  Principal Component Analysis , 2002 .

[39]  Gary R. Bradski,et al.  ORB: An efficient alternative to SIFT or SURF , 2011, 2011 International Conference on Computer Vision.