HISTOGRAM OF EDGE SEGMENT CURVATURES FOR TEXTURE RECOGNITION

Year 2018, Volume: 19 Issue: 3, 784 - 795, 01.09.2018

Mehmet Koç Cihan Topal

Abstract

Texture recognition is one of the active fields in pattern recognition. Researchers have been searching for the best representation of a texture image for decades. The majority of methods use appearance-based properties of texture images to generate a feature descriptor. In this paper, we propose novel feature descriptor, namely histogram of edge segment curvatures (HESC) which extracts edge segments of an input image and construct a histogram from quantized curvature values of them. Therefore, HESC unveils geometric information of texture images by utilizing curve strengths for each pixel along the edge segments. We show that the proposed feature descriptor is robust against rotation and translation. We also extend HESC descriptor to emphasis the contribution of small curvature values. We carry out several experiments in UIUC texture dataset and compare the performance of the proposed HESC descriptor to well-known Local Binary Pattern (LBP). The proposed texture descriptor outperforms LBP in terms of recognition accuracy.

Keywords

Texture recognition, texture descriptor, curvature, feature extraction

References

• Rellier G, Descombes X., Falzon F, Zerubia J. Texture feature analysis using a gauss-Markov model in hyperspectral image classification. IEEE T Geosci Remote 2004; 42(7):1543-1551.
• Mirzapour F, Ghassemian H. Improving hyperspectral image classification by combining spectral, texture, and shape features. Int J Remote Sens 2015; 36(4): 1070-1096.
• Guo Z, Zhang L, Zhang D, Mou X. Hierarchical multiscale LBP for face and palmprint recognition. In: IEEE International Conference on Image Processing, 2010; Hong Kong,China. pp. 4521-4524.
• Kassner A, Thornhill R. Texture analysis: a review of neurologic MR imaging applications. AJNR Am J Neuroradiol 2010; 3(5); 809-816.
• Ahonen T, Hadid A, Pietikainen M. Face description with local binary patterns: Application to face recognition. IEEE Trans Pattern Anal Mach Intell 2006; 28(12): 2037-2041.
• Shan C, Gong S, McOwan P. Robust facial expression recognition using local binary patterns. In IEEE International Conference on Image Processing, 2005; Genova, Italy. pp. II-370-3.
• Xie X. A review of recent advances in surface defect detection using texture analysis techniques. Electronic Letters on Computer Vision and Image Analysis 2008; 7(3): 1-22.
• Ojala T, Pietikäinen M, Mäenpää T. Multi-resolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans Pattern Anal Mach Intell 2002; 7(24): 971-987.
• Crosier M, Griffin L. Using Basic Image Features for Texture Classification. Int J Comput Vis 2010; 88(3): 447-460.
• Guo Y, Zhao G, Pietikäinen M. Discriminative features for texture description. Pattern Recognit 2012; 45(10): 3834-3843.
• Ojala T, Pietikäinen M, Harwood D. A comparative study of texture measures with classification based on feature distributions. Pattern Recognit 1996; 29: 51-59.
• Yang M, Kpalma K, Ronsin J. A survey of shape feature extraction techniques. Pattern Recogniti, P. Yin, Ed., IN-TECH, 2008.
• Kazak N, Koc M. Some variants of spiral LBP in texture recognition. IET Image Process 2018, In Press,doi: 10.1049/iet-ipr.2017.1261.
• Gou Z, Zhang L, Zhang D. A completed modelling of local binary pattern operator for texture classification. IEEE Trans. Image Process 2010; 19(6): 1657-1663.
• Kazak N, Koc M. Performance analysis of spiral neighbourhood topology based local binary patterns in texture recognition. International Journal of Applied Mathematics, Electronics and Computers 2016; 4: 338-341.
• Kazak N, Koc M, Benligiray B, TopalC. A comparison of classification methods for local binary patterns. In: IEEE Signal Processing and Communication Application Conference 2016; Zonguldak, Turkey. pp. 805-808.
• Shang J, Chen C, LiangH. Object recognition using rotation invariant local binary pattern of significant bit planes. IET Image Process 2016; 10(9): 662-670.
• Yadav R, Nishchala N, Gupta A, Rastogi V. Retrieval and classification of shape-based objects using Fourier, generic Fourier, and wavelet-Fourier descriptors technique: A comparative study. Opt Lasers Eng. 2007; 45(6): 695-708.
• Wang Y, Lee K, Toraichi K. Multiscale curvature-based shape representation using B-spline wavelets. IEEE Trans. Image Process 1999; 8(10): 1586-1592.
• Topal C, Akinlar C. Edge Drawing: A combined real-time edge and segment detector. J Vis Commun Image Represent 2012; 23(6): 862-872.
• Canny J. A computational approach to edge detection. IEEE Trans Pattern Anal Mach Intell 1986; 8(6): 679-698.
• Lazebnik S, Schmid C, Ponce J. A Sparse Texture Representation Using Local Affine Regions. IEEE Trans Pattern Anal Mach Intell 2005; 27(8):1265-1278.