تشخيص خرابي بافت به کمک تبديل پيچک
محورهای موضوعی : مهندسی برق و کامپیوتر
بي‌بي مريم معاشري
1
(دانشگاه شهيد باهنر کرمان)
حسین نظام‌آبادی‌پور
2
(دانشگاه شهید باهنر کرمان)
سعيد سريزدي
3
(دانشگاه شهيد باهنر کرمان)
سهيل آزادي‌نيا
4
(دانشگاه شهيد باهنر کرمان)
کلید واژه: تشخيص خرابي بافت تبديل پيچک بردار ويژگي,
چکیده مقاله :
در اين مقاله سامانه‌اي کارآمد و دقيق براي توصيف خرابي‌ها در انواع بافت بر اساس تبديل پيچک ارائه شده است. ايده اصلي، در نظر گرفتن خرابي‌هاي بافت به‌صورت ناپيوستگي‌هاي يک‌بعدي در سيگنال (تابع) دوبعدي تصوير است. بر اساس اين ايده، مناسب‌ترين ابزار جهت توصيف خرابي‌ها، تبديل جهتي پيچک است. ابتدا در مرحله آموزش، نمونه‌هايي از بلوک‌هاي بافت سالم و معيوب جمع‌آوري شده و بر روي هر بلوک، تبديل پيچک اعمال مي‌شود. سپس براي هر بلوک يک بردار ويژگي بر اساس زيرباندهاي حاصل از تبديل پيچک تشکيل مي‌شود. در يک فرايند پيشنهادي بردار ويژگي برجسته براي بافت مورد نظر تعيين مي‌شود. پس از آن سطوح آستانه مناسب براي تشخيص بلوک‌هاي خراب بافت، تنظيم مي‌شود. در مرحله آزمايش، از هر بلوک بافت بردار ويژگي برجسته مربوط به آن استخراج شده و بافت مذکور با توجه به سطوح آستانه طبقه‌بندي مي‌شود. نتايج شبيه‌سازي‌ها نشان مي‌دهد که سامانه پيشنهادي نسبت به روشي که مبتني بر جابه‌جايي ميانگين است، دقت بيشتري در آشکارسازي بافت‌هاي معيوب داشته و در فرآيند تشخيص خرابي، نسبت به نوع بافت حساسيت کمتري از خود نشان مي‌دهد.
This article, an efficient system for texture defect detection based on curvelet transform is presented. The main idea is to model the defects in the texture image as one-dimensional discontinuities. Based on this idea, the curvelet transform is the most efficient method for describing defects. First, in the learning phase, training samples of intact and defected blocks of the texture image are collected and transformed to the curvelet domain. Next, for each block a feature vector based on curvelet sub-bands is extracted and using a proposed method some important and effective features are determined for the desired texture. Then, a proper threshold for detecting defected from intact blocks is determined. In the performance phase, a vector containing the important features from each block of the texture is extracted and then the block by is classified. The results of simulation show that the proposed system is superior to the mean shift method in detecting defected texture blocks, and is less sensitive to the type of texture.
[1] A. Monadjemi, Towards Efficient Texture Classification and Abnormality Detection, Ph. D. Thesis, Bristol University, Oct. 2004.
[2] H. Yan - Fang and S. Peng-Fei, "Mean shift texture surface detection based on WT and COM feature image selection," J. of Zhejiang University Science A, vol. 7, no. 6, pp. 969-975, ???. 2006.
[3] J. L. Sobral, Leather Inspection Based on Wavelets, Springer - Verlag Berlin Heidelberg, pp. 682-688, 2005.
[4] H. Yan - Fang and S. Peng - Fei, "An adaptive level - selecting wavelet transform for texture defect detection," Image and Vision Computing, vol. 25, no. 8, pp. 1239-1248, Aug. 2007.
[5] X. Xie and M. Mirmehdi, "TEXEMS: texture exemplars for defect detection on random textured surfaces," IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 29, no. 8, pp. 1454-1464, Aug. 2007.
[6] P. M. Mahjan, S. R. Kolhe, and P. M. Patil, "A review of automatic fabric defect detection techniques," Advances in Computational Research, vol. 1, no. 2, pp. 18-29, 2009.
[7] C. K. Mohan, M. Vijayaraghavan, and J. Rengarajan, "Real time texture defect detection using sub-band domain feature extraction," Global Signal Processing Expo and Conf., Santa Clara , US, 27-30 Sep. 2004.
[8] A. Latif - Amet, A. Ertuzun, and A. Ercil, "An efficient method for texture defect detection: sub-band domain co-occurrence matrices," Image and Vision Computing, vol. 18, no. 6-7, pp. 543-553, May 2000.
[9] Y. X. Zhi, G. K. H. Pang, and N. H. C. Yung, "Fabric defect detection using adaptive wavelet," in Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing, vol. 6, pp. 3697-3700, 7-11 May 2001.
[10] G. Fan and X. G. Xia, "Wavelet - based texture analysis and synthesis using hidden markov models," IEEE Trans. Circuits and Systems, vol. 50, no. 1, pp. 106-120, Jan. 2003.
[11] E. Kulak, Analysis of Textural Image Features for Content Based Retrieval, Master of Science Thesis, Sabanc1 University, Oct. 2002.
[12] M. C. Lee and C. M. Pun, "Texture classification using dominant wavelet packet energy features," in Proc. of 4th IEEE Southwest Symposium on Image Analysis and Interpretation, pp. 301-304, 2-4 Apr. 2000.
[13] A. Latif-Amet, A. Ertuzun, and A. Ercil, "Texture defect detection using subband domain co-occrrence matrices," in Proc. IEEE Southwest Symp. on Image Analysis and Interpretation, pp. 205-210, 5-7 Apr. 1998.
[14] G. Lambert and F. Bock, "Wavelet methods for texture defect detection," in IEEE Proc. of the Int. Conf. on Image Processing, vol. 3, pp. 201-204, 26-29 Oct. 1997.
[15] D. A. Karras and B. G. Mertzios, Improved Defect Detection in Manufacturing Using Novel Multidimensional Wavelet Feature Extraction Involving Vector Quantization and PCA Techniques, Springer - Verlag Berlin Heidelberg, 2002.
[16] D. Comaniciu and P. Meer, "Mean shift: a robust approach toward feature space analysis," IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 24, no. 5, pp. 603-619 , May 2002.
[17] J. R. Smith and S. F. Chang, "Transform features for texture classification and discrimination in large image databases," in Proc. IEEE Int. Conf. on Image Proc., vol. 3, pp. 407-411, 13-16 Nov. 1994.
[18] J. R. Smith and S. F. Chang, "Automated binary texture feature sets for image retrieval," in Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing, vol.4, pp. 2239-2242, Atlanta, GA, US, 7-10 May 1994.
[19] T. Chang and C. C. J. Kuo, "Texture analysis and classification with tree-structured wavelet transform," IEEE Trans. Image Processing, vol. 2, no. 4, pp. 429-441, Oct. 1993.
[20] A. Kundu and J. L. Chen, "Texture classification using qmf bank - based subband decomposition," Graphical Models and Image Processing, vol. 54, no. 5, pp. 369-384, Sep. 1992.
[21] M. H. Gross, R. Koch, L. Lippert, and A. Dreger, "Multiscale image texture analysis in wavelet spaces," in Proc. IEEE Int. Conf. on Image Processing, vol. 3, pp. 412-416, 13-16 Nov. 1994.
[22] K. S. Thyagarajan, T. Nguyen, and C. Persons, "A maximum likelihood approach to texture classification using wavelet transform," in Proc. IEEE Int. Conf. on Image Proc., vol. 2, pp. 640-644, 13-16 Nov. 1994.
[23] T. Randen and J. H. Husoy, "Filtering for texture classification: a comparative study," IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 21, no. 4, pp. 291-310, Apr. 1999.
[24] N. P. N. J. Sargunar and R. Sukanesh, "Texture defect detection technique for MRI knee image," Int. J. of Recent Trends in Engineering, vol. 2, no. 1, pp. 183-187, Nov. 2009.
[25] K. N. Siavabalan and D. Ghanadurai, "Detection of defects in digital texture images using segmentation," Int. J. of Engineering Science and Technology, vol. 2, no. 10, pp. 5187-5191, Oct. 2010.
[26] ع. ر. وحدت و ر. صفابخش، "تشخيص و دسته‌بندي عيوب بافت پارچه به کمک تجزيه موجک،" چهارمين کنفرانس ماشين بينايي و پردازش تصوير ايران، بهمن 1385.
[27] M. Ghazvini, S. A. Monadjemi, N. Movahhedinia, and K. Jamshidi, "Defect detection of tiles using 2D - wavelet transform and statistical features," World Academy of Science, Engineering and Technology, vol. 49, pp. 901-904, Jan. 2009.
[28] N. D. Minh, Directional Multiresolution Image Representations, Ph. D Thesis, Oct. 2001.
[29] E. J. Candes and D. L. Donoho, "Ridgelets: a key to higher- dimensional intermittency?" Phil. Trans. Royal Society London, vol. 357, no. 1760, pp. 2495-2509, Sep. 1999.
[30] N. D. Minh and M. Vetterli, "The finite ridgelet transform for image representation," IEEE Trans. on Image Processing, vol. 12, no. 1, pp. 16-28, Jan. 2003.
[31] L. Dettori and L. Semler, "A comparison of wavelet, ridgelet, and curvelet - based texture classification algorithms in computed tomography," Elsevier Computers in Biology and Medicine, vol. 37, no. 4, pp. 486-498, Apr. 2007.
[32] S. Arivazhagan, L. Ganesan, and T. G. Subash Kumar, "Texture classification using ridgelet transform," in Proc. 6th IEEE Int. Conf. on Computational Intelligence and Multimedia Applications, pp. 321-326, 16-18 Aug. 2005.
[33] E. J. Candès, L. Demanet, D. L. Donoho, and L. Ying, "Fast discrete curvelet transforms," Multiscale Modeling and Simulation, vol. 5, no. 3, pp. 861-899, 2005.
[34] E. J. Candès and D. L. Donoho, "Continuous curvelet transform: I. Resolution of the wavefront set," Applied and Computational Harmonic Analysis, vol. 19, no. 2, pp. 162-197, Sep. 2005.
[35] ب. رجايي و ح. ر. پوررضا، "طبقه‌بندي بافت مستقل از دوران و مقياس با استفاده از تبديل پيچک،" چهارمين كنفرانس ماشين بينايي و پردازش تصوير ايران، بهمن 1385.
[36] S. Arivazhagan, L. Ganesan, and T. G. Subash Kumar, "Texture classification using curvelet statistical and co - occurrence features," in Proc. 18th IEEE Int. Conf. on Pattern Recognition, vol. 2, pp. 938-941, 2006
[37] L. Semler and L. Dettori, "Curvelet-based texture classification of tissues in computed tomography," in Proc. IEEE Int. Conference on Image Processing, pp. 2165-2168, 8-11 Oct. 2006.
[38] L. Shen and Q. Yin, "Texture classification using curvelet transform," in Proc. Int. Symp. on Information Processing, pp. 319-324, 21-23 Aug. 2009.
[39] ب. م. معاشري، ح. نظام‌آبادي‌پور و س. سريزدي، "تشخيص خرابي بافت به کمک تبديل پيچک،" پنجمين کنفرانس ماشين بينايي، تبريز، ايران، آبان 1387.
[40] ح. محمدتقي‌زاده، ح. نظام‌آبادي‌پور و س. سريزدي، "مقايسه ويژگي‌هاي آماري و معيارهاي عدم شباهت در بازيابي تصوير بر اساس محتوا در حوزه تبديل پيچک،" پانزدهمين کنفرانس سالانه انجمن کامپيوتر ايران، تهران، ايران، اسفند 1388.
[41] M. L. Raymer, W. F. Punch, E. Gooddman, L. A. Kuhn, and A. K. Jain, "Dimentionality reduction using genetic algorithm," IEEE Trans. on Evolutionary Computation, vol. 4, no. 2, pp. 164- 171, Jul. 2000.
[42] S. Maldonado and R. Weber, "A wrapper method for feature selection using support vector machines," Information Sciences, vol. 179, no. 13, pp. 2208-2217, Jun. 2009.