HYBRID CLASSIFICATION ANN, DWT AND FRACTAL ANALYSIS FOR DIRECTIONAL TEXTURES

  • S. ZEHANI Dept. Electrical Engineering, Kasdi Merbab University, Ouargla, Algeria
  • M. MIMI Laboratory of Signals and Systems (LSS), Abdelhamid Ibn Badis University, Mostaganem, Algeria
  • S. SBAA Dept. Electrical Engineering, Mohamed Khider University, Biskra, Algeria
  • A. TALEB-AHMED LAMIH UMR CNRS-UVHC 8201, Valenciennes and Hainaut-Cambresis University Valenciennes, France
  • A. TOUMI Dept. Electrical Engineering, Mohamed Khider University, Biskra, Algeria

Résumé

In this paper, we present a hybrid directional classification of anisotropic textures. Our proposed method based to yield a robust attributes vector to classify the different anisotropic textures. A robust fractal analysis is put forward by hybridization of the statistical fractal with Discrete Wavelets Transform (DWT). Beside, to enhance the quality of texture, a preprocessing stage using histogram equalization is carried out. Then for a given direction from 0° to 360° by a step of 10°, we applied the DWT using Daubechies wavelets (db5) to the corresponding direction where the approximate image is inputted to Differential Box-Counting Method (DBCM) in order to yield a robust Fractal Dimension (FD) estimated in wavelets domain. We formed the vector attributes to each texture that correspond to the inputs of our Artificial Neurons Network (ANN) classifier. The originality of our work, reside in the use of the Daubechies Wavelets (db5), in particular the use of approximate image with the fractal analysis, by, estimating the directional FD and using the directional classification based on ANN classifier. To validate our algorithm, we used two classes of the Brodatz textures database. Performance classification was assessed by ROC analysis and confusion matrix. We report a successful separation of the two classes, after different training. Area under-curve (AUC) values for training, validation and testing are 1, 0.96 and 1 and classification rates are 94.1%, 85.7%, 85.7% respectively, with the classification rate for all data is 91.7% and a fail classification is 8.3%.

Références

[1] M. Nixon, Feature Extraction and Image Processing for Computer Vision. Academic Press, 3rd Edition, NY, 2012.
[2] Haralick, R.M., K. Shanmugam, and I.H. Dinstein, “Textural features for image classification,” IEEE Trans. Systems, Man and Cybernetics, (6), pp. 610-621, Nov. 1973.
[3] B.B. Mandelbrot, The fractal geometry of nature. W.H. Freeman & Co Ltd Publisher, Macmillan, 1983.
[4] K.Falconer, Fractal geometry: mathematical foundations and applications. John Wiley & Sons, 2004.
[5] S. S. Chen, J. M. Keller, and R. M. Crownover, “On the calculation of fractal features from images,” IEEE Trans. Pattern Analysis and Machine Intelligence TPAMI, vol. 15, no. 10, pp. 1087–1090, Oct. 1993.
[6] Zuñiga, A.G., J.B. Florindo, and O.M. Bruno, “Gabor wavelets combined with volumetric fractal dimension applied to texture analysis,” Pattern Recognition Letters, 36, pp. 135-143, 2014.
[7] André Ricardo Backes, Dalcimar Casanova, Odemir Martinez, Brunob, “Color texture analysis based on fractal descriptors”, Pattern Recognition, 45(5), pp. 1984-1992, 2012.
[8] W-Y. Hsu, C-C. Lin, M-S. Ju and Y-N. Sun, “Wavelet-based fractal features with active segment selection: Application to single-trial EEG data,” Journal of Neuroscience Methods, 163(1), pp. 145-160, 2007.
[9] Taleb-Ahmed, A., P. Dubois, and E. Duquenoy. (2003). Analysis methods of CT-scan images for the characterization of the bone texture: First results. Pattern recognition letters. 24(12), pp. 1971-1982.
[10] Khan M. Iftekharuddin,Wei Jia, Ronald Marsh, “Fractal analysis of tumor in brain MR images”, Machine Vision and Applications, Springer-Verlag 13, 2003, pp: 352–362.
[11] André Ricardo Backes, Odemir Martinez Bruno , “Fractal and Multi-Scale Fractal Dimension analysis: a comparative study of Bouligand-Minkowski method”, INFOCOMP Journal of Computer Science, 7(2), pp. 74-83, 2012.
[12] Lopes, R. and N. Betrouni. (2009). Fractal and multifractal analysis: a review. Medical image analysis. 13(4), pp. 634-649.
[13] D. Sankar, T. Thomas, “Fractal Features based on Differential Box Counting Method for the Categorization of Digital Mammograms”, International Journal of Computer Information System and Industrial Management Application (IJCISIM) , 2, pp. 011-019, 2010.
[14] Luiz G. Hafemann, “An Analysis of Deep Neural Networks for Texture Classification” Master’s degree, Curitiba, Brazil, 2014.
[15] Ali H. Al-Timemy, Fawzi M. Al-Naima and Nebras H. Qaeeb, “Probabilistic Neural Network for Breast Biopsy Classification” MASAUM Journal of Computing, 1 (2), Sep. 2009.
[16] Harrar, K., et al. (2012, ). “Osteoporosis assessment using Multilayer Perceptron neural networks” Presented at the 3rd International Conference IPTA.
[17] Dr.Mohammad V.Malakooti, Zahed FerdosPanah, Dr.Seyyed Mohsen Hashemi, “Image Recognition Method based on Discreet Wavelet Transform (DWT) and Singular Value Decomposition (SVD)”, ISBN: 978-0-9853483-3-5, SDIWC, 2013.
[18] [6] Tae Jin Kang, Soo Chang Kim, In Hwan Sun, Jae Ryoun Youn and Kwansoo Chung, “Fabric Surface Roughness Evaluation Using Wavelet-Fractal Method, Part I: Wrinkle, Smoothness and Seam Pucker”, Textile Res. J. 75(11), 2005, pp. 751–760.
Publiée
2017-02-05
Comment citer
ZEHANI, S. et al. HYBRID CLASSIFICATION ANN, DWT AND FRACTAL ANALYSIS FOR DIRECTIONAL TEXTURES. Courrier du Savoir, [S.l.], v. 22, fév. 2017. ISSN 1112-3338. Disponible à l'adresse : >http://revues.univ-biskra.dz/index.php/cds/article/view/1907>. Date de consultation : 18 déc. 2017