Unsupervised texture-based image segmentation through pattern discovery

This paper presents a new efficient technique for unsupervised segmentation of textured images that aims at incorporating the advantages of supervision for discriminating texture patterns. First, a pattern discovery stage that relies on a clustering algorithm is utilized for determining the texture patterns of a given image based on the outcome of a multichannel Gabor filter bank. Then, a supervised pixel-based classifier trained with the feature vectors associated with those patterns is used to classify every image pixel into one of the sought texture classes, thus yielding the final segmentation. Multi-sized evaluation windows following a top-down approach are utilized during pixel classification in order to improve accuracy both inside and near boundaries of regions of homogeneous texture. Results with synthetic compositions and with complex real images are presented and discussed. The proposed technique is also compared with alternative texture segmentation approaches.

[1]  Maria Petrou,et al.  Spectral unmixing of mixed pixels for texture boundary refinement , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[2]  Hossein Mobahi,et al.  Natural Image Segmentation with Adaptive Texture and Boundary Encoding , 2009, ACCV.

[3]  Maria Petrou,et al.  Image processing - dealing with texture , 2020 .

[4]  Dorin Comaniciu,et al.  Mean Shift: A Robust Approach Toward Feature Space Analysis , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Ilan Shimshoni,et al.  Mean shift based clustering in high dimensions: a texture classification example , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[6]  Ian Burns,et al.  Measuring texture classification algorithms , 1997, Pattern Recognit. Lett..

[7]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[8]  Domenec Puig,et al.  Pixel Classification by Divergence-Based Integration of Multiple Texture Methods and Its Application to Fabric Defect Detection , 2003, DAGM-Symposium.

[9]  Inderjit S. Dhillon,et al.  Weighted Graph Cuts without Eigenvectors A Multilevel Approach , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  William M. Rand,et al.  Objective Criteria for the Evaluation of Clustering Methods , 1971 .

[11]  Andries Petrus Engelbrecht,et al.  An overview of clustering methods , 2007, Intell. Data Anal..

[12]  Domenec Puig,et al.  Automatic texture feature selection for image pixel classification , 2006, Pattern Recognit..

[13]  Jitendra Malik,et al.  From contours to regions: An empirical evaluation , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[14]  B. S. Manjunath,et al.  Texture Features for Browsing and Retrieval of Image Data , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  Allen Y. Yang,et al.  Unsupervised segmentation of natural images via lossy data compression , 2008, Comput. Vis. Image Underst..

[16]  Nello Cristianini,et al.  Large Margin DAGs for Multiclass Classification , 1999, NIPS.

[17]  Jitendra Malik,et al.  Normalized cuts and image segmentation , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[18]  K. Ruba Soundar,et al.  Texture image segmentation using combined features from spatial and spectral distribution , 2006, Pattern Recognit. Lett..

[19]  Majid Mirmehdi,et al.  Segmentation of Color Textures , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[20]  Jiebo Luo,et al.  Two-stage texture segmentation using complementary features , 2000, Proceedings 2000 International Conference on Image Processing (Cat. No.00CH37101).

[21]  Domenec Puig,et al.  Efficient distance-based per-pixel texture classification with Gabor wavelet filters , 2008, Pattern Analysis and Applications.

[22]  Matti Pietikäinen,et al.  Unsupervised texture segmentation using feature distributions , 1997, Pattern Recognit..

[23]  Tae Jin Kang,et al.  Texture classification and segmentation using wavelet packet frame and Gaussian mixture model , 2007, Pattern Recognit..

[24]  S. Abe,et al.  Why pairwise is better than one-against-all or all-at-once , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[25]  Jitendra Malik,et al.  A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[26]  B. S. Manjunath,et al.  EdgeFlow: a technique for boundary detection and image segmentation , 2000, IEEE Trans. Image Process..

[27]  Trygve Randen,et al.  Filtering for Texture Classification: A Comparative Study , 1999, IEEE Trans. Pattern Anal. Mach. Intell..