NOISY TEXTURES DETECTION USING NEURAL NETWORK CLASSIFICATION

А. В. Науменко, С. С. Кривенко, М. С. Зряхов, В. В. Лукин

Abstract


The possibility of detecting texture areas of the image distorted by an additive uncorrelated noise has been analyzed with help of the classifier based on neural network learning. We investigated the following sets of input parameters (attributes): relative local variance, Harris detector, simple textures detector, detector based on discrete cosine transform. It is shown that detection performance depends on the number of input characters and on type of used input parameters. Issues of training the neural network and the application of a trained classifier for image processing with different textures are discussed.

Keywords


texture, detection, image noise, neural network, training

References


Pratt, W. K. Digital Image Processing. Fourth Edition. N. Y., Wiley-Interscience Publ., USA, 2007. 1429 p.

Schowengerdt, R. Remote Sensing: Models and Methods for Image Processing. Academic Press, 2006. 560 p.

Haralick, R., Dori, D. A pattern recognition approach to detection of complex edges. Pattern Recognit. Lett. 16, no. 5, 1995, pp. 517–529.

Haralick, R. M. Textural features for image classification. IEEE Trans. Syst., Man, Cybern., vol. 3, no. 6, 1973, pp. 610–621.

Partio, M. Applying texture and color features to natural image retrieval. Proc. Finnish Signal Processing Symposium (FINSIG ’03), Tampere, Finland, May 2003, pp. 199–203.

Bevz, E. G. Algoritmy segmentacii dlja zadach teksturnogo analiza s primeneniem metoda sintaksicheskogo opisanija tekstur [Segmentation algorithms for texture analysis tasks using the syntax description of the method of textures]. Doklady Belorusskogo gosudarstvennogo universiteta informatiki i radiojelektroniki, Belorussia, 2011, no. 8 (62), pp. 9-13.

Krylov, V. N., Poljakova, M. V. Chastotnodetektornyj metod teksturnoj segmentacii izobrazhenij [Frequency detection method of texture image segmentation]. AAJeKS Informacionno-izmeritel'nye sistemy, 2005, no. 2(16), pp. 40-46.

Leung, T. Representing and recognizing the visual appearance of materials using three-dimensional textons. Intl. Journal of Computer Vision, no. 43, 2001, pp. 29–44.

Micusik, B., Hanbury, A. Supervised texture detection in images. Proceedings of 11-th International Conference on Computer Analysis of Images and Patterns, Versailles, France, Sept. 2005, pp. 441-448.

Nunes, J. C., Niang, O., Bouaoune, Y., Delechelle, E., Bunel, Ph. Texture analysis based on the bidimensional empirical mode decomposition with graylevel co-occurrence models. Proc. 7th International Symposium on Signal Processing and Its Applications. Paris, France, vol. 2, July 2003, pp. 633–635,

Lukin, V. V., Tsymbal, O. V., Ponomarenko, N. N., Egiazarian, K. O. and Astola, J. T. Image processing with texture feature preservation by three-state locally adaptive filter. Image and Signal Processing for Remote Sensing IX, Barcelona, Spain, vol. 5238 of SPIE Proceedings, September 2003, pp. 120–131.

Tsymbal, O. V., Lukin, V. V., Ponomarenko, N. N., Zelensky A. A., Egiazarian, K. O., Astola, J. T. Three-state Locally Adaptive Texture Preserving Filter for Radar and Optical Image Processing. EURASIP Journal on Applied Signal Processing, no 8, May 2005, pp. 1185-1204.

Aiazzi B., Alparone, L., Baronti, S., Carla, R. Adaptive texture-preserving filtering of multitemporal ERS-1 SAR images. Proc. IEEE International Geoscience and Remote Sensing Symposium (IGARSS ’97), Singapore, vol. 4, August 1997, pp. 2066–2068.

Rubel, O., Ponomarenko, N., Lukin, V., Egiazarian, K., Astola, J. HVS-based local analysis of denoising efficiency for DCT-based filters. Proceedings of the Conference Problems of Infocommunications. Science and Technology. Kharkov, Ukraine, October 2015, pp. 189-192.

Perry, S. W., Wong, H. S., Guan, L. Adaptive Image Processing: A Computational Intelligence Perspective. CRC Press Publ., Boca Raton, USA, 2002. 376 p.

Rubel, A., Lukin, V., Pogrebniak, O. Efficiency of DCT-based denoising techniques applied to texture images. Proceedings of MCPR, Cancun, Mexico, LNCS 8495, June 2014, pp. 111-120.

Rubel, A., Lukin, V., Uss, M., Vozel, B. Egiazarian, K., Pogrebnyak, O. Efficiency of texture image enhancement by DCT-based filtering. Neurocomputing, vol. 175, part B, January 2016, pp. 948–965.

Lukin, V., Ponomarenko, N., Egiazarian, K., HVS-Metric-Based Performance Analysis Of Image Denoising Algorithms. Proceedings of EUVIP. Paris, France, 2011, pp. 156-161.

Gilboa, G., Sochen, N., Zeevi, Y. Y. Variational Denoising of Partly-Textured Images by Spatially Varying Constraints. IEEE Transactions on Image Processing, vol. 15, no. 8, 2006, pp. 2281-2289.

Zuo, W., Zhang, L., Song, C., Zhang, D. Texture Enhanced Image Denoising via Gradient Histogram Preservation. Proceedings of CVPR, Portland, OR, USA, 2013, pp. 1203-1210.

Chatterjee, P., Milanfar, P. Is Denoising Dead? IEEE Trans. Image Processing, vol. 19, no. 4, 2010, pp. 895-911.

Dabov, K., Foi, A., Katkovnik, V., Egiazarian, K. Image denoising by sparse 3D transform-domain collaborative filtering. IEEE Transactions on Image Processing, vol. 16, no. 8, 2007, pp. 2080-2095.

Vozel, B., Chehdi, K., Klaine, L., Lukin, V. V., Abramov, S. K. Noise identification and estimation of its statistical parameters by using unsupervized variational classification. Proceedings of ICASSP, Toulouse, France, vol. 2, 2006, pp 841-844.

Uss, M. L., Vozel, B., Lukin, V., Chehdi, K. Image Informative Maps for Component-wise Estimating Parameters of Signal-Dependent Noise. Journal of Electronic Imaging, vol. 22, no. 1, 2013, pp. 1-18.

Krivenko, S. S., Naumenko, A. V., Lukin, V. V. Obnaruzhenie teksturnyh uchastkov SVMklassifikatorom na izobrazhenijah pri nalichii pomeh [Detection of texture areas SVM-classifier at the images in the presence of interference], Radiojelektronnye i komp'juternye sistemy, no. 2(72), 2015, pp. 50-57.

Scholkopf B., Smola, A. J. Learning with Kernels. MIT Press Publ., Cambridge, USA, 2002. 38 p.

Bishop, C. Pattern Recognition and Machine Learning. Springer Science+Business Media, LLC, 2006. 738 p.

Karu, K., Jain, A., Bolle, R. Is there any Texture in the Image? IEEE Pattern recognition 1996 Proceedings, vol. 2, 1996, pp. 770 -774.

Kang, X., Han, C., Yang, Y., Tao, T. SAR image edge detection by ratio-based Harris Method. ICASSP 2006 Proceedings, vol. 2, May 2006, pp. 837- 840.

Naumenko, A. V., Lukin, V. V. Detektirovanie granic na izobrazhenijah s pomoshh'ju iskusstvennoj nejronnoj seti [Boundaries detection in images using artificial neural network]. Aviacionno-kosmicheskaja tehnika i tehnologija, vol. 2, 2012, pp. 101-110.

Ling, С., Huang, J., Zhang, H. AUC: a statistically consistent and more discriminating measure than accuracy. Proceedings of IJCAI, Mexico, 2003, pp. 519- 524.




DOI: https://doi.org/10.32620/reks.2016.1.05

Refbacks

  • There are currently no refbacks.