Texture Classification based on First Order Circular and Elliptical Ternary Direction Pattern Matrix

  • Authors

    • K Subba Reddy
    • V Vijaya Kumar
    • A P. Siva Kumar
    https://doi.org/10.14419/ijet.v7i3.27.18504
  • Isotropic, Anisotropic, Derivative, Ternary pattern

  • Local binary pattern (LBP) captures isotropic structural information and completely fails in representing anisotropic information, however the horizontal elliptical LBP (H-ELBP) and vertical elliptical LBP (V-ELBP) represents partial anisotropic information only. In our earlier work we have derived “circular and elliptical-LBP (CE-LBP)†captures both isotropic and anisotropic structural information with a feature vector size equivalent to LBP and it is easy to implement and invariant to monotonic illumination changes. The LBP, local ternary pattern (LTP), CE-LBP and most of the extensions of LBP descriptor basically ignore the directional information. To address this and to capture both isotropic and anisotropic directional information, this paper proposes a “circular and elliptical ternary direction pattern matrix (CE-TDPM)â€. The CE-TDPM encodes the relationship between the central pixel and two of its neighboring pixel located in different angles (α, β) with different directions. The CE-TDPM evaluated the possible direction variation pattern for central pixel by measuring the first order derivate relationship among the horizontal and vertical neighbors (0o vs. 90o; 90o vs. 180o; 180o vs. 270o; 270o vs. 0o) and derived a unique code. The performance of the proposed method is compared with various other existing methods using the benchmark texture databases viz. Brodtaz, UIUC, Outex and MIT-VisTex. The performance analysis shows the efficiency of the proposed method over the existing methods.

     

     

  • References

    1. [1] M. Haas, J. Rijsdam, B. Thomee, and M. S. Lew, “Relevance feedback: Perceptual learning and retrieval in bio-computing, photos, and videoâ€, in Proc. 6th ACM SIGMM Int. Workshop Multimedia Inf. Retrieval, 2004, pp. 151–156.

      [2] X.-Y.Wang, B.-B. Zhang, and H.-Y. Yang, “Content-based image retrieval by integrating color and texture featuresâ€, Multimedia Tools Appl., vol. 68, no. 3, pp. 545–569, 2014

      [3] G. Zhao, M. Barnard, and M. Pietikainen, “Lipreading with local spatiotemporal descriptorsâ€, IEEE Trans.Multimedia, vol. 11, no. 7, pp. 1254– 1265, Nov. 2009.

      [4] Y. D. Chun, N. C. Kim, and I. H. Jang, “Content-based image retrieval Using multiresolution color and texture featuresâ€, IEEE Trans.Multimedia, vol. 10, no. 6, pp. 1073–1084, Oct. 2008.

      [5] J. Ren, X. Jiang, J. Yuan, and N. Magnenat-Thalmann, “Sound-event classification using robust texture features for robot hearingâ€, IEEE Trans. Multimedia, vol. 19, no. 3, pp. 447–458, Mar. 2017

      [6] X. Liu and D.Wang, “Image and texture segmentation using local spectral histogramsâ€, IEEE Trans. Image Process., vol. 15, no. 10, pp. 3066–3077,Oct. 2006.

      [7] X. Wang, C. Zhang, and Z. Zhang, “Boosted multi-task learning for face verification with applications to web image and video searchâ€, in Proc. IEEE Conf. Comput. Vision Pattern Recognit., 2009, pp. 142–149.

      [8] T. Ojala, M. Pietik¨ainen, and T. M¨aenp¨a¨a, “Multiresolution gray-scale and rotation invariant texture classification with local binary patternsâ€, IEEE Trans. Pattern Anal. Mach. Intell., vol. 24, no. 7, pp. 971–987, Jul. 2002.

      [9] T. Song, H. Li, F. Meng, Q. Wu, and B. Luo, “Exploring space-frequency co-occurrences via local quantized patterns for texture representationâ€, Pattern Recogit., vol. 48, no. 8, pp. 2621–2632, 2015.

      [10] Y. Dong, J. Feng, L. Liang, L. Zheng, and Q. Wu, “Multiscale samplingbased texture image classificationâ€, IEEE Signal Process. Lett., vol. 24,no. 5, pp. 614–618, May 2017.

      [11] T. Song and H. Li, “WaveLBP based hierarchical features for image classificationâ€, Pattern Recognit. Lett., vol. 34, no. 12, pp. 1323–1328, 2013.

      [12] D. T. Nguyen, Z. Zong, P. Ogunbona, and W. Li, “Object detection using non-redundant local binary patternsâ€, in Pro. 17th Int. Conf. Image Process., Sep. 2010, pp. 4609–4612.

      1. Satpathy, X. Jiang, andH. L. Eng, “LBP-based edge-texture features for object recognitionâ€, IEEE Trans. Image Process., vol. 23, no. 5, pp. 1953– 1964, May 2014.

      [13] M. Heikkil¨a, M. Pietik¨ainen, and C. Schmid, “Description of interestregions with local binary patternsâ€, Pattern Recognit., vol. 42, no. 3,pp. 425–436, 2009.

      [14] LiWangDong-ChenHe, “Texture classification using texture spectrumâ€, Pattern Recognition Volume 23, Issue 8, 1990, Pages 905-910.

      [15] T. Ojala, M. Pietik¨ainen, and D. Harwood, “A comparative study of texture measures with classification based on featured distributionsâ€, Pattern Recognit., vol. 29, no. 1, pp. 51–59, 1996.

      [16] U.Kandaswamy, S. A. Schuckers, and D. Adjeroh, “Comparison of texture analysis schemes under nonideal conditionsâ€, IEEE Trans. Image Process., vol. 20, no. 8, pp. 2260–2275, Aug. 2011

      [17] G. S. Xia, G. Liu, X. Bai, and L. Zhang, “Texture characterization usingshape co-occurrence patternsâ€, IEEE Trans. Image Process., vol. 26,no. 10, pp. 5005–5018, Oct. 2017.

      [18] F. Juefei-Xu and M. Savvides, “Subspace-based discrete transform encoded local binary patterns representations for robust periocular matching on NIST’s face recognition grand challengeâ€, IEEE Trans. Image Process., vol. 23, no. 8, pp. 3490–3505, Aug. 2014.

      [19] T. Song, H. Li, F. Meng, Q. Wu, and J. Cai, “LETRIST: Locally encoded transform feature histogram for rotation-invariant texture classificationâ€, IEEE Trans. Circuits Syst. Video Technol., to be published.

      [20] O. G. Cula and K. J. Dana, “Compact representation of bidirectional texture functionsâ€, in Proc. IEEE Conf. Comput. Vision Pattern Recognit., 2001, vol. 1, pp. I-1041–I-1047.

      [21] T. Leung and J. Malik, “Representing and recognizing the visual appearance of materials using three-dimensional textonsâ€, Int. J. Comput. Vision, vol. 43, no. 1, pp. 29–44, 2001.

      [22] D. G. Lowe, “Distinctive image features from scale-invariant keypointsâ€,Int. J. Comput. Vision, vol. 60, no. 2, pp. 91–110, 2004.

      [23] N. Dalal and B. Triggs, “Histograms of oriented gradients for humandetectionâ€, in Proc. IEEE Conf. Comput. Vision Pattern Recognit., 2005,vol. 1, pp. 886–893.

      [24] X. Meng, Z. Wang, and L. Wu, “Building global image features for scenerecognitionâ€, Pattern Recognit., vol. 45, no. 1, pp. 373–380, 2012.

      [25] X. Tan and B. Triggs, “Enhanced local texture feature sets for face recognition under difficult lighting conditionsâ€, IEEE Trans. Image Process., vol. 19, no. 6, pp. 1635–1650, Jun. 2010.

      [26] Y. Guo, G. Zhao, and M. Pietik¨ainen, “Texture classification using a linear configuration model based descriptorâ€, in Proc. Brit. Mach. Vision Conf., Pietik¨a, pp. 1–10.

      [27] G. Sharma, S. ulHussain, and F. Jurie, “Local higher-order statistics (LHS) for texture categorization and facial analysisâ€, in Proc. Eur. Conf. Comput. Vision, 2012, pp. 1–12.

      [28] L. Wolf, T. Hassner, and Y. Taigman, “Descriptor based methods in the wildâ€, in Proc. Workshop Faces in “Real-Life†Images: Detection, Alignment, Recognit., 2008, pp. 1–14.

      [29] Z. Guo, L. Zhang, and D. Zhang, “A completed modeling of local binarypattern operator for texture classificationâ€, IEEE Trans. Image Process.,vol. 19, no. 6, pp. 1657–1663, Jun. 2010.

      [30] X. Wu and J. Sun, “Joint-scale LBP: A new feature descriptor for texture classificationâ€, Vis. Comput., vol. 33, pp. 317–329, 2015.

      [31] L. Liu, P. Fieguth, Y. Guo, X. Wang, and M. Pietik¨ainen, “Local binary features for texture classification: Taxonomy and experimental studyâ€, Pattern Recognit., vol. 62, pp. 135–160, 2017.

      [32] N. Zhang, R. Farrell, F. Iandola, and T. Darrell, “Deformable part descriptors for fine-grained recognition and attribute predictionâ€, in Proc. IEEE Int. Conf. Comput. Vision, 2013, pp. 729–736.

      [33] B. Sujatha, V.Vijaya Kumar, P. Harini, “A new logical compact LBP co-occurrence matrix for texture analysisâ€, International Journal of Scientific & Engineering Research (IJSER) , Vol.3, Iss.2, 2012, pp.1-5, ISSN 2229-5518.

      [34] V. VijayaKumar ,Jangala. SasiKiran , V.V. HariChandana, “ An effective age classification using topological features based on compressed and reduced grey level model of the facial skinâ€, International journal of image, graphics and signal processing (IJIGSP), , Vol.6, Iss.1, 2013, pp.9-17, ISSN: 2074-9082.

      [35] J. Chen et al., “WLD: A robust local image descriptorâ€, IEEE Trans.Pattern Anal. Mach. Intell., vol. 32, no. 9, pp. 1705–1720, Sep. 2010.

      [36] J. Mao, J. Zhu, and A. L. Yuille, “An active patch model for real world texture and appearance classificationâ€, in Proc. Eur. Conf. Comput. Vision, 2014, pp. 140–155.

      [37] Y. Xu, X. Yang, H. Ling, and H. Ji, “A new texture descriptor using multifractal analysis in multi-orientation wavelet pyramidâ€, in Proc. IEEE Conf. Comput. Vision Pattern Recognit., 2010, pp. 161–168.

      [38] R. Margolin, L. Zelnik-Manor, and A. Tal, “OTC: A novel local descriptorfor scene classificationâ€, in Proc. Eur. Conf. Comput. Vision., 2014,pp. 377–391.

      [39] T. Gao, X. Zhao, M. Xiang, and Z. Liu, “Texture feature descriptor usingauto salient feature selection for scale-adaptive improved local difference binaryâ€, Multidimensional Syst. Signal Process., vol. 28, pp. 281–292, 2017.

      [40] M. Cimpoi, S. Maji, I. Kokkinos, S. Mohamed, and A. Vedaldi, “Describing textures in the wildâ€, in Proc. IEEE Conf. Comput. Vision Pattern Recognit., 2014, pp. 3606–3613.

      [41] E. Simo-Serra et al., “Discriminative learning of deep convolutionalfeature point descriptorsâ€, in Proc. IEEE Int. Conf. Comput. Vision, 2015, pp. 118–126.

      [42] E. Simo-Serra et al., “Discriminative learning of deep convolutionalfeature point descriptorsâ€, in Proc. IEEE Int. Conf. Comput. Vision, 2015, pp. 118–126.

      [43] M. Cimpoi, S. Maji, and A. Vedaldi, “Deep filter banks for texture recognition and segmentationâ€, in Proc. IEEE Conf. Comput. Vision Pattern Recognit., 2015, pp. 3828–3836.

      [44] L. Sifre and S. Mallat, “Rotation, scaling and deformation invariant scattering for texture discriminationâ€, in Proc. IEEE Conf. Comput. Vision Pattern Recognit., 2013, pp. 1233–1240.

      [45] T.-Y. Lin and S. Maji, “Visualizing and understanding deep texture representationsâ€, in Proc. IEEE Conf. Comput. Vision Pattern Recognit., 2016, pp. 2791–2799.

      [46] V. Andrearczyk and P. F. Whelan, “Using filter banks in convolutionalneural networks for texture classificationâ€, Pattern Recognit. Lett., vol. 84, pp. 63–69, 2016.

      [47] J. Li, J. M. Bioucas-Dias, and A. Plaza, “Semi-supervised hyperspectralimage classification using soft sparse multinomial logistic regressionâ€,IEEE Geosci. Remote Sens. Lett., vol. 10, no. 2, pp. 318–322, Mar. 2013.

      [48] J. Li, J. M. Bioucas-Dias, and A. J. Plaza, “Spectral-spatial hyper spectral image segmentation using subspace multinomial logistic regression and Markov random fieldsâ€, IEEE Trans. Geosci. Remote Sens., vol. 50, no. 3, pp. 809–823, Mar. 2012.

      [49] F.Melgani and L. Bruzzone, “Classification of hyperspectral remote sensing images with support vector machinesâ€, IEEE Trans. Geosci. Remote Sens., vol. 42, no. 8, pp. 1778–1790, Aug. 2004.

      [50] M. Fauvel, J. A. Benediktsson, J. Chanussot, and J. R. Sveinsson, “Spectral and spatial classification of hyperspectral data using SVMs and morphological profilesâ€, IEEE Trans. Geosci. Remote Sens., vol. 46, no. 11, pp. 3804–3814, Nov. 2007.

      [51] J. Xia, M. D. Mura, J. Chanussot, P. Du, and X. He, “Random subspace ensembles for hyperspectral image classification with extended morphological attribute profilesâ€, IEEE Trans. Geosci. Remote Sens., vol. 53, no. 9, pp. 4768–4786, Sep. 2015.

      [52] F. Ratle, G. Camps-Valls, and J.Weston, “Semisupervised neural networks for efficient hyperspectral image classificationâ€, IEEE Trans. Geosci. Remote Sens., vol. 48, no. 5, pp. 2271–2282, May 2010.

      [53] J. Xia, J. Chanussot, P. Du, and X. He, “Spectral-spatial classification for hyperspectral data using rotation forests with local feature extraction and Markov random fieldsâ€, IEEE Trans. Geosci. Remote Sens., vol. 53, no. 5, pp. 2532–2546, May 2015.

      [54] M. Elad, Sparse and Redundant Representations—From Theory to Applications in Signal and Image Processing. New York, NY, USA: Springer, 2010.

      [55] J. Mairal, M. Elad, and G. Sapiro, “Sparse representation for color image restorationâ€, IEEE Trans. Image Process., vol. 17, no. 1, pp. 53–69, Jan. 2008.

      [56] J. Wright, A. Y. Yang, A. Ganesh, S. S. Sastry, and Y. Ma, “Robust facerecognition via sparse representationâ€, IEEE Trans. Pattern Anal. Mach. Intell., vol. 31, no. 2, pp. 210–227, Feb. 2009.

      [57] M. Elad and M. Aharon, “Image denoising via sparse and redundantrepresentations over learned dictionariesâ€, IEEE Trans. Image Process.,vol. 15, no. 12, pp. 3736–3745, Dec. 2006.

      [58] R. O. Duda, P. E. Hart, and D. G. Stork, Pattern Classification. 2nd Ed.Hoboken, NJ, USA: Wiley, 2012.

      [59] Y. Chen, N. M. Nasrabadi, and T. D. Tran, “Hyperspectral image classification via kernel sparse representationâ€, IEEE Trans. Geosci. Remote Sens., vol. 51, no. 1, pp. 217–231, Jan. 2013

      [60] Y. Chen, N. M. Nasrabadi, and T. D. Tran, “Hyperspectral image classification using dictionary-based sparse representationâ€, IEEE Trans. Geosci. Remote Sens., vol. 49, no. 10, pp. 3973–3985, Oct. 2011.

      [61] J. Li, H. Zhang, Y. Huang, and L. Zhang, “Hyperspectral image classification by nonlocal joint collaborative representation with a locally adaptive dictionaryâ€, IEEE Trans. Geosci. Remote Sens., vol. 52, no. 6, pp. 3707–3719, Jun. 2014.

      [62] J. Li, H. Zhang, and L. Zhang, “Column-generation kernel nonlocal joint collaborative representation for hyperspectral image classificationâ€, ISPRS J. Photogramm., vol. 94, pp. 25–36, 2014.

      [63] E. Zhang, X. Zhang, H. Liu, and L. Jiao, “Fast multifeature joint sparserepresentation for hyperspectral image classificationâ€, IEEE Geosci.Remote Sens. Lett., vol. 12, no. 7, pp. 1397–1401, Jul. 2015.

      [64] H. Zhang, J. Li,Y.Huang, and L. Zhang, “A nonlocal weighted joint sparse representation classification method for hyperspectral imageryâ€, IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens, vol. 7, no. 6, pp. 2056–2065, Jun. 2014.

      [65] W. Li, Q. Du, and M. Xiong, “Kernel collaborative representation withTikhonov regularization for hyperspectral image classificationâ€, IEEEGeosci. Remote Sens. Lett., vol. 12, no. 1, pp. 48–52, Jan. 2015.

      [66] L. Gan, P. Du, J. Xia, and Y. Meng, “Kernel fused representation-basedclassifier for hyperspectral imageryâ€, IEEE Geosci. Remote Sens. Lett.,vol. 14, no. 5, pp. 684–688, May 2017.

      [67] Petpon, S. Srisuk, Face recognition with local line binary pattern, in: International Conference on Image and Graphics, 2009, pp. 533–539.

      [68] S. ulHussian and B. Triggs, “Visual recognition using local quantized patternsâ€, in Proc. Eur. Conf. Comput. Vis., 2012, pp. 716–729.

      [69] S. Liao, A. C. S. Chung, Face recognition by using elongated local binary patterns with average maximum distance gradient magnitude, in: Proceedings of Asian Conference on Computer Vision (ACCV), 2007, pp. 672–679

      [70] L. Nanni, A. Lumini, S. Brahnam, Local binary patterns variants as texture descriptors for medical image analysis, Artif. Intell. Med. 49 (2) (2010) 117–125

      [71] K. Subba Reddy, V. Vijaya Kumar, A.P. Siva Kumar, Classification of Textures Using a New Descriptor Circular and Elliptical-LBP (CE-ELBP), International Journal of Applied Engineering Research ISSN 0973-4562 Volume 12, Number 19 (2017) pp. 8844-8853

      [72] P. Brodatz, Texture, 1968, “A Photographic Album for Artists and Designers†, Reinhold, New York, 1968.

      [73] S. Lazebnik, C. Schmid, and J. Ponce, “A sparse texture representationusing local affine regionsâ€, IEEE Trans. Pattern Anal. Mach. Intell.,vol. 27, no. 8, pp. 1265–1278, Aug. 2005.

      [74] http://www.outex.oulu.fi/index.php?page=image_database.

      [75] MIT Vision and Modeling Group, Cambridge, „Vision texture‟, http://vismod.media.mit.edu/pub/

  • Downloads

  • How to Cite

    Subba Reddy, K., Vijaya Kumar, V., & P. Siva Kumar, A. (2018). Texture Classification based on First Order Circular and Elliptical Ternary Direction Pattern Matrix. International Journal of Engineering & Technology, 7(3.27), 601-608. https://doi.org/10.14419/ijet.v7i3.27.18504