Classification of texture based on Bag-of-Visual-Words through complex networks

Abstract Over the last years complex data (e.g. images) have been growing in a very fast pace. This demands the ability to describe and to categorize them. To solve this problem it is essential to develop efficient and effective vision-based expert techniques. Hence, the cornerstone of our work is to propose a new methodology, called BoVW-CN, that combines Bag-of-Visual-Words and complex networks for describing keypoints detected in a given image. Our insight is that describing just the relevant points of an image we can achieve a more cost-effective and better image description. The obtained results testify that BoVW-CN, applied to public image datasets, outperforms the widely used state-of-the-art methods. We not only obtained good accuracies (e.g. 78.18%), but also performed analyses to find the best trade-off between computational cost and accuracy. Besides, to the best of our knowledge, our work is the first one to propose such integration of Bag-of-Visual-Words and complex networks through a texture-based focus.

[1]  Siome Goldenstein,et al.  Image classification based on bag of visual graphs , 2013, 2013 IEEE International Conference on Image Processing.

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

[3]  Gabriela Csurka,et al.  Visual categorization with bags of keypoints , 2002, eccv 2004.

[4]  S. Theodoridis,et al.  Chapter 4 – Nonlinear Classifiers , 2009 .

[5]  João Paulo Papa,et al.  Supervised pattern classification based on optimum-path forest , 2009 .

[6]  Andrew Zisserman,et al.  The devil is in the details: an evaluation of recent feature encoding methods , 2011, BMVC.

[7]  Robert Azencott,et al.  Texture Classification Using Windowed Fourier Filters , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Wesley Nunes Gonçalves,et al.  Texture Analysis by Bag-Of-Visual-Words of Complex Networks , 2015, CIARP.

[9]  Anil K. Jain,et al.  Statistical Pattern Recognition: A Review , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  Alexandre X. Falcão,et al.  Motion segmentation and activity representation in crowds , 2009 .

[11]  Thorsten Joachims,et al.  Text Categorization with Support Vector Machines: Learning with Many Relevant Features , 1998, ECML.

[12]  Gabriela Csurka,et al.  Adapted Vocabularies for Generic Visual Categorization , 2006, ECCV.

[13]  Pierre Tirilly,et al.  Language modeling for bag-of-visual words image categorization , 2008, CIVR '08.

[14]  André Ricardo Backes,et al.  A Complex Network-Based Approach for Texture Analysis , 2010, CIARP.

[15]  Tao Mei,et al.  Contextual Bag-of-Words for Visual Categorization , 2011, IEEE Transactions on Circuits and Systems for Video Technology.

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

[17]  Arun Siddharth Konagurthu,et al.  On the origin of distribution patterns of motifs in biological networks , 2008, BMC Systems Biology.

[18]  João Paulo Papa,et al.  Automatic visual dictionary generation through Optimum-Path Forest clustering , 2012, 2012 19th IEEE International Conference on Image Processing.

[19]  Fabrício Martins Lopes,et al.  A Complex Network-Based Approach to the Analysis and Classification of Images , 2015, CIARP.

[20]  Mark E. J. Newman,et al.  The Structure and Function of Complex Networks , 2003, SIAM Rev..

[21]  Léon Bottou,et al.  Local Learning Algorithms , 1992, Neural Computation.

[22]  Luc Van Gool,et al.  SURF: Speeded Up Robust Features , 2006, ECCV.

[23]  Anil K. Jain.  Data clustering: 50 years beyond K-means , 2010, Pattern Recognit. Lett..

[24]  M. Gavrilova,et al.  A Survey of Landmark Recognition Using the Bag-of-Words Framework , 2013 .

[25]  Matti Pietikäinen,et al.  Outex - new framework for empirical evaluation of texture analysis algorithms , 2002, Object recognition supported by user interaction for service robots.

[26]  Argyris Kalogeratos,et al.  Movie segmentation into scenes and chapters using locally weighted bag of visual words , 2009, CIVR '09.

[27]  Pabitra Mitra,et al.  A survey on image retrieval performance of different bag of visual words indexing techniques , 2014, Proceedings of the 2014 IEEE Students' Technology Symposium.

[28]  Fabrício Martins Lopes,et al.  Combining SURF descriptor and complex networks for face recognition , 2016, 2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI).

[29]  André Ricardo Backes,et al.  Texture analysis and classification: A complex network-based approach , 2013, Inf. Sci..

[30]  C. V. D. Malsburg,et al.  Frank Rosenblatt: Principles of Neurodynamics: Perceptrons and the Theory of Brain Mechanisms , 1986 .

[31]  Célia A. Zorzo Barcelos,et al.  Texture characterization via improved deterministic walks on image-generated complex network , 2015, 2015 IEEE International Conference on Image Processing (ICIP).

[32]  Phil Brodatz,et al.  Textures: A Photographic Album for Artists and Designers , 1966 .

[33]  V. Latora,et al.  Complex networks: Structure and dynamics , 2006 .