Abstract
In this study, we propose a simple and efficient texture-based algorithm for image segmentation. This method constitutes computing textons and bag of words (BOWs) learned by support vector machine (SVM) classifiers. Textons are composed of local magnitude coefficients that arise from the Q-Shift Dual-Tree Complex Wavelet Transform (DT-CWT) combined with color components. In keeping with the needs of our research context, which addresses land cover mapping from remote images, we use a few small texture patches at the training stage, where other supervised methods usually train fully representative textures. We accounted for the scale and rotation invariance issue of the textons, and three different invariance transforms were evaluated on DT-CWT-based features. The largest contribution of this study is the comparison of three classification schemes in the segmentation algorithm. Specifically, we designed a new scheme that was especially competitive and that uses several classifiers, with each classifier adapted to a specific size of analysis window in texton quantification and trained on a reduced data set by random selection. This configuration allows quick SVM convergence and an easy parallelization of the SVM-bank while maintaining a high segmentation accuracy. We compare classification results with textons made using the well-known maximum response filters bank and speed up robust features features as references. We show that DT-CWT textons provide better distinguishing features in the entire set of configurations tested. Benchmarks of our different method configurations were made over two substantial textured mosaic sets, each composed of 100 grey or color mosaics made up of Brodatz or VisTex textures. Lastly, when applied to remote sensing images, our method yields good region segmentation compared to the ENVI commercial software, which demonstrates that the method could be used to generate land cover maps and is suitable for various purposes in image segmentation.
Similar content being viewed by others
References
Shotton J, Winn J, Rother C, Criminisi A (2006) Textonboost: Joint appearance, shape and context modeling for multi-class object recognition and segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp 1–15
Tuceyran M, Jain AK (1998) Chapter 2.1 Texture analysis. The Handbook of Pattern Recognition and Computer Vision. 2nd edn. World Scientific Publishing, Singapore, pp 207–248
Soltanian-Zadeh H, Rafiee-Rad F, Pourabdollah-Nejad S (2004) Comparison of multiwavelet, wavelet, haralick, and shape features for microcalcification classification in mammograms. Pattern Recognit 37(10):1973–1986
Fauzi MFA, Lewis PH (2006) Automatic texture segmentation for content-based image retrieval application. Pattern Anal Appl 9(4):307–323. doi:10.1007/s10044-006-0042-x
Galun M, Sharon E, Basri R, Brandt A (2003) Texture segmentation by multiscale aggregation of filter responses and shape elements. In: IEEE International Conference on Computer Vision, vol 1. IEEE Computer Society, pp 716–723
Yacoob Y, Davis L (2007) Segmentation using meta-texture saliency. In: International Conference of Computer Vision (ICCV 2007)
Lo EHS, Pickering MR, Frater MR, Arnold JF (2011) Image segmentation from scale and rotation invariant texture features from the double dyadic dual-tree complex wavelet transform. Image Vis Comput 29(1):15–28
Savelonas Michalis A, Iakovidis Dimitris K, Maroulis Dimitris (2008) Lbp-guided active contours. Pattern Recognit Lett 29(9):1404–1415
Haindl M, Mikeš S (2004) Model-based texture segmentation. In: Image analysis and recognition, Springer, Berlin, pp 306–313
Zhou Hailing, Zheng Jianmin, Wei Lei (2013) Texture aware image segmentation using graph cuts and active contours. Pattern Recognit 46(6):1719–1733
Sang Hak Lee, Hyung Il Koo, Nam Ik Cho (2010) Image segmentation algorithms based on the machine learning of features. Pattern Recognit Lett 31(14):2325–2336
Julesz B (1994) Dialogues on Perception. The MIT Press, Cambridge, MA
Malik J, Belongie S, Shi J, Leung T (1999) Textons, contours and regions: cue integration in image segmentation. Int Conf Comput Vis 2:918–925
Leung T, Malik J (2001) Representing and recognizing the visual appareance of materials using three-dimensional textons. Int J Comput Vis 43(1):29–44
van der Maaten LJP, Postma E (2007) Texton-based texture classification. In: Proceedings of Belgium-Netherlands Artificial Intelligence Conference
Blas MR, Agrawal M, Sundaresan A, and Konolige K (2008) Fast color/texture segmentation for outdoor robots. In: IEEE / RSJ International Conference on Intelligent Robots and Systems, pp 4078–4085
Varma M, Zisserman A (2005) A statistical approach to texture classification from single images. Int J Comput Vis 62(1–2):61–81
Zhu S-C, Guo C-E, Wu Y, Wang Y (2005) What are textons ? Int J Comput Vis 62(1–2):121–143
Alvarez S, Fermandez, Vanrell M (2012) Texton theory revisited: a bag-of-words approach to combine textons. Pattern Recognit 45(12):4312–4325
Xu Yong, Huang Sibin, Ji Hui, Ferm++ller Cornelia (2012) Scale-space texture description on sift-like textons. Comput Vis Image Underst 116(9):999–1013
Nguyen H-G, Fablet R, Boucher J-M (2010) Spatial statistics of visual keypoints for texture recognition. In: Daniilidis Kostas, Maragos Petros, Paragios Nikos (eds) Computer Vision ECCV 2010, vol 6314., Lecture Notes in Computer ScienceSpringer, Berlin / Heidelberg, pp 764–777
Kingsbury NG (2001) Complex wavelets for shift invariant analysis and filtering of signals. J Appl Comput Harmon Anal 10(3):234–253
De Rivaz P (2000) Complex wavelet based image analysis and synthesis. PhD Thesis, University of Cambridge
Selesnick IW, Baraniuk RG, Kingsbury NG (2005) The dual-treeree complex wavelet transform. IEEE Signal Processing Magazine 22(6):123–151
Bay H, Ess A, Tuytelaars T, Van Gool L (2008) Speeded-up robust features (surf). Comput. Vis. Image Underst. 110(3):346–359
Mallat SG (1989) A theory for multiresolution signal decomposition: the wavelet representation. IEEE Trans Pattern Anal Mach Intell 11(7):674–693
Lu CS, Chung PC, Chen CF (1997) Unsupervised texture segmentation via wavelet transform. Pattern Recognit 30(5):729–742
Kim SC, Kang TJ (2007) Texture classification and segmentation using wavelet packet frame and gaussian mixture model. Pattern Recognit 40(4):1207–1221
Elik T, Tjahjadi T (2011) Multiscale texture classification and retrieval based on magnitude and phase features of complex wavelet subbands. Comput Electr Eng 37(5):729–743
Kingsbury NG (2006) Rotation-invariant local feature matching with complex wavelets. In European Conference on Signal Processing (EUSIPCO)
Lo EHS, Pickering M, Frater M, Arnold J (2004) Scale and rotation invariant texture features from the dual-tree complex wavelet transform. In: IEEE International Conference on Image Processing (Singapore), pp 227–230
David Arthur, Sergei Vassilvitskii. K-means++ (2007) The advantages of careful seeding. In Proceedings of the Eighteenth Annual ACM-SIAM Symposium on Discrete Algorithms, SODA ’07, Society for Industrial and Applied Mathematics, Philadelphia, pp 1027–1035
Jones DG, Malik J (1992) A computational framework for determining stereo correspondence from a set of linear spatial filters. In: Image and Vision Computing, pp 395–410
Vapnik VN (1998) Statistical learning theory. Wiley, New York
Chih-Chung Chang, Chih-Jen Lin (2011) LIBSVM: A library for support vector machines. ACM Transactions on Intelligent Systems and Technology, 2:27:1–27:27. http://www.csie.ntu.edu.tw/cjlin/libsvm
Liang K-H, Tjahjadi T (2006) Adaptative scale fixing for multiscale texture segmentation. IEEE Trans Image Process 15:249–256
Borne F, Guillobez S (1994) A new approach in remote sensing image analysis for natural environment cartography. In: Surface and Atmospheric Remote Sensing: Technologies, Data Analysis and Interpretation, International Geoscience and Remote Sensing Symposium (IGARSS), pp 1805–1807
Garcia MA, Puig D (2007) Supervised texture classification by integration of multiple texture methods and evaluation windows. Image Vis Comput 25(7):1091–1106
Envi software version 4.7
Robert M, Haralick K, Shanmugam, Its’Hak Dinstein (1973) Textural features for image classification. IEEE Systems, Man, and Cybernetics Society, SMC-3:610–621
Anderson R, Kingsbury NG, Fauqueur J (2005) Multiscale object features from clustered complex wavelet coefficients. In IEEE 13th Workshop on Statistical Signal Processing, pp 437–442
Kurtz Camille, Passat Nicolas, GançArski Pierre, Puissant Anne (2012) Extraction of complex patterns from multiresolution remote sensing images: A hierarchical top-down methodology. Pattern Recognit 45(2):685–706
Acknowledgments
This work was supported by the Shiva ANR Project (French National Agency for Research http://www.shiva-anr.org/). The high-spatial resolution SPOT5 images were accessed due to the ISIS 2010 program of the French Space Agency (CNES) and SPOT Image (http://www.isis-cnes.fr/). The authors would like to thank J. M. Roger, C. Lelong, V. Deblauwe, R. Bose and M. Jones for their helpful comments, which led to improvements in this study.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Kennel, P., Fiorio, C. & Borne, F. Supervised image segmentation using Q-Shift Dual-Tree Complex Wavelet Transform coefficients with a texton approach. Pattern Anal Applic 20, 227–237 (2017). https://doi.org/10.1007/s10044-015-0491-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10044-015-0491-1