آشکارسازی شکستگی‌های سنگ مخزن مبتنی بر آنالیز بافت جهتی و نگاشت خودسازمان‌ده

نویسندگان

دانشگاه شهید چمران اهواز - دانشکده مهندسی - گروه برق

چکیده

به‌دلیل تأثیر بسزایی که شکستگی‌ها بر تولید و برداشت بهتر و مؤثرتر از چاه دارند، شناسایی این پدیده‌ها، موضوعی بسیار بااهمیت است. نمودارهای تصویری، ابزار بسیار قوی برای مطالعه شکستگی‌ها در چاه‌ها هستند. در یک نمودار تصویری، یک شکستگی به شکل منحنی سینوسی دیده می‌شود. در این مقاله، ابتدا با استفاده از روش‌های استخراج ویژگی، مانند بانک فیلتر گابور، گشتاورهای زرنیک، گشتاورهای مستقل هفت‌گانه هیو و تبدیل والش-هادامارد جهتی، ویژگی‌های مفید استخراج‌شده و سپس برای کلاسه‌بندی نمودار تصویری، شبکه عصبی SOM بکار گرفته‌شده است. نتایج آزمایشی نشان داد که الگوریتم پیشنهادی به‌طور موفقیت‌آمیز و با دقت بالایی قادر به تشخیص شکستگی‌های موجود در نمودارهای تصویری است. در الگوریتم پیشنهادی، از روش‌های استخراج ویژگی استفاده شد که برای استخراج ویژگی اشیاء بافت، مناسب می‌باشند. نتایج نشان می‌دهند که دقت روش پیشنهادی برای استخراج پیکسل‌های شکستگی، بسیار بالا است و همچنین حساسیت کمی به نویز در نمودارهای تصویری دارد. الگوریتم پیشنهادی در این مقاله بر روی دو دسته از دیتاست‌های تصویری FMI و RMI اعمال شد و نتیجه کلاسه‌بندی در مقایسه با سایر الگوریتم‌های پیشنهادی، از دقت بهتری برخوردار است.

کلیدواژه‌ها

عنوان مقاله [English]

Detection of Reservoir Fractures based on Directional Texture Analysis and Self-Organizing Map

نویسندگان [English]

  • F. Taiebi
  • G. Akbarizadeh
  • E. Farshidi
Department of Electrical Engineering, Faculty of Engineering, Shahid Chamran University of Ahvaz, Ahvaz, Iran
چکیده [English]

Due to the significant impact of fractures on the better and more effective production and harvesting, the identification of this phenomenon is a very important. Imaging logs are very powerful tools to study the fractures in the boreholes. In an imaging log, a fracture is seen in the form of a sine curve. In this paper, first, the useful features are extracted by using feature extraction methods such as the Gabor filter bank, Zernike moments, Hu's seven invariant moments and directional Walsh-Hadamard transform, and then, a SOM neural network is used to classify the imaging log. The experimental results showed that the proposed algorithm is able to detect the existing fractures successfully with high accuracy in the imaging logs. In the proposed algorithm, the feature extraction methods are used, which are suitable for extracting the feature of texture objects. The results show that the accuracy of the proposed method is very high to extract fracture pixels, and it has also low sensitivity to noise in the imaging logs. The proposed algorithm in this paper was applied to two types of FMI and RMI image datasets, and the result of the classification has better accuracy in comparison with other algorithms.

کلیدواژه‌ها [English]

  • Fracture
  • imaging log
  • sine curve
  • feature extraction
  • Gabor filter bank
  • Zernike moments
  • Hu's seven invariant moments
  • directional Walsh-Hadamard transform
  • SOM neural network

مراجع

[1] W. Al-Sit, W. Al-Nuaimy, M. Mar and A. Al-Ataby. “Visual texture for automated characterisation of geological features in borehole televiewer imagery,ˮ Journal of Applied Geophysics, vol. 119, pp. 139–146, 2015.
[2] S. Teniou and M. Meribout. “A multimodal image reconstruction method using ultrasonic waves and electrical resistance tomography,” IEEE Transactions on Image Processing. vol. 24, no. 11, Nov. 2015.
[3] U. Ahmed and D. N. Meehan, Unconventional Oil and Gas Resources: Exploitation and Development, CRC Press, Technology & Engineering - 860 pages, 2015.
[4] A. Shahinpour, Borehole Image Log Analysis for Sedimentary Environment and Clay Volume Interpretation, Petroleum Geosciences, pp. 1-84, September 2013.
[5] M. Seifallahi, B. Tokhmchi, A. Soleimani and A. Ahmadi Fard, “A novel methodology for fracture extraction from borehole image logs,” The First International Conference Oil, Gas, Petrochemical And Power Plant, Tehran: SID, 2013.
[6] فرهاد خوشبخت، محمد محمدنیا و علی‌محمد باقری. «تحلیل شکستگی‌ها و شناسایی تنش‌ها در مخازن هیدروکربوری با استفاده از لاگ‌های تصویری»، سومین کنفرانس مکانیک سنگ ایران، دانشگاه امیرکبیر، 24 الی 26 مهر 1386.
[7] GH. Saedi, B. Soleimani and SH. Esmaeilzadeh. “Fracture characterization utilizing FMI, velocity deviation logs, core description and thin sections data,” Neues Jahrbuch für Geologie und Paläontologie - Abhandlungen. vol. 284, no. 1, pp. 15-28, April 2017.
[8] A. Kingdon, M. W. Fellgett and J. D. O. Williams. “Use of borehole imaging to improve understanding of the in-situ stress orientation of Central and Northern England and its implications for unconventional hydrocarbon resources,” Marine and Petroleum Geology. vol. 73, pp. 1-20, May 2016.
[9] W. Wang, H. Liao and Y. Huang, “Rock fracture tracing based on image processing and SVM,ˮ Natural Computation, ICNC, Third International Conference on, vol. 1, pp. 632–635 (1em plus 0.5em minus 0.4em IEEE), 2007.
[10] C. He and W. Wang, “A PCNN-based edge detection algorithm for rock fracture imagesˮ Symposium on Photonics and Optoelectronic (SOPO), pp. 1–4 (1em plus 0.5em minus 0.4em IEEE), 2010.
[11] X. Chen-Yin, H. W. Hao, Zh. Bin. Wang, K. Huang and Q. Lui, “FMI image based rock structure classification using classifier combination,ˮ Neural Computing and Applications, vol. 20, no. 7, pp. 955-963, 2011.
[12] S. Assous, P. Elkington, S. Clark and J. Whetton. “Automated detection of planar geologic features in borehole images,ˮ Geophysics, vol. 79, no. 1, 2013.
[13] M. Voorn, U. Exner and A. Rath. Multiscale. “Hessian fracture filtering for the enhancement and segmentation of narrow fractures in 3D image data,” Computers & Geosciences. vol. 57, Pp. 44–53, 2013.
[14] Zh. Xiang, Zh. Wei and X. Xiaoling. “Rapid detection of bedding boundaries based on borehole images,” Computer Modelling & New Technologies. vol. 18, no. 10, pp. 207-211, 2014.
[15] M. Shafiezadeh, M. Ziaee and B. Tokhmchi. “A new approach towards precise planar feature characterization using image analysis of FMI image: case study of gachsaran oil field well no. 245, southwest of Iran,” Journal of Petroleum Science and Technology. vol. 5, no. 2, pp. 51-58, 2015.
[16]  مصطفی جاوید، حسین معماریان، رضا آقایی زاده ظروفی، بهزاد تخم‌چی، فرهاد خوشبخت و سید مهدی مطهری. «تشخیص شکستگی‌ها در نمودارهای تصویری الکتریکی با استفاده از تکنیک‌های پردازش تصویر و الگوریتم ژنتیک»، پژوهش نفت، سال بیست و دوم، شماره 72، صفحه 85-98، آذر 1391.
[17]  محمود سیف‌اللهی، بهزاد تخم‌چی، علی سلیمانی و علیرضا احمدی فرد. «شناسایی هوشمند شکستگی‌های طبیعی باز در چاه‌های کربناته با استفاده از چاه نمودارهای تصویری»، سی‌ودومین گردهمایی و نخستین کنگره بین‌المللی تخصصی علوم زمین، بهمن 1391.
[18] S. Ergin and O. Kilinc, “A new feature extraction framework based on wavelets for breast cancer diagnosis,ˮ Computers in Biology and Medicine, vol. 51, pp. 171-182, 2014.
[19] L. Zhenjiang, M. Yu, H. Wei, L. Hongsheng, Zh. Jian, L. Wanhu and L. Baosheng. “Texture-based classification of different single liver lesion based on SPAIR T2W MRI images,” BMC Medical Imaging. vol. 17, no. 42, pp. 1-9, 2017.
[20] X. Sun, Q. Qu, N. M. Nasrabadi and T. D. Tran. “Structured priors for sparse-representation-based Hyperspectral image classification,” IEEE Geoscience and Remote Sencing Letters. vol. 11, no. 7, pp. 1235 – 1239, 2014.
[21] B. Cyganek, “One-class support vector ensembles for image segmentation and classification,ˮ Journal of Mathematical Imaging and Vision, vol. 42, no. 2, pp. 103–117, 2012.
[22] Sh. Shubhi and Kh. Pritee. “Computer-aided diagnosis of malignant mammograms using Zernike moments and SVM,” Journal of Digital Imaging, vol. 28, no. 1, pp. 77–90, February 2015.
[23] Y. Zhao, Sh. Wang, X. Zhang and  H. Yao. “Robust hashing for image authentication using Zernike moments and local features,” IEEE Transactions on Information Forensics and Security vol. 8, no. 1, pp. 55-63, Jan 2013.
[24] M. K. Hu, “Visual pattern recognition by moment invariants,” IRE Trans. Inform. Theory, vol. IT-8, pp. 179-187, Feb. 1962.
[25] A. A. Pandian and R. Balasubramanian. “Fusion of contourlet transform and Zernike moments using content based image retrieval for MRI brain tumor images,” Indian Journal of Science & Technology. vol. 9, no. 29, 8 pages, August 2016.
[26] M. Teague, “Image analysis via the general theory of moments,” J. Opt. Soc. Amer, vol. 70, no. 8, pp. 920-930, Aug. 1980.
[27] G. Yang, V. Lalande, L.Chen, N. Azzabou, T. Larcher, J. D. de Certaines, H. Shu and J. L. Coatrieux. “MRI texture analysis of GRMD dogs using orthogonal moments: A preliminary study,” IRBM. vol. 36, no. 4, pp. 213-219, August 2015.
[28] X. Ch. Yuan, Ch. M. Pun and C. L. P. Chen, “Geometric invariant watermarking by local Zernike moments of binary image patches,” journal Signal Processing vol. 93, pp. 2087–2095, 2013.
[29] Y. Zhang, Sh. Wang, P. Sun and P. Phillips, “Pathological brain detection based on Wavelet entropy and Hu moment invariants,” Bio-Medical Materials and Engineering, vol. 26, pp. 283–290, 2015.
[30] A. Bhardwaj, M. Kaur and A. Kumar, “Recognition of plants by leaf image using moment invariant and texture analysis,” International Journal of Innovation and Applied Studies, vol. 3, no. 1, pp. 237-248, 2013.
[31] A. A. Goshtasby. Theory and Applications of Image Registration, 1st Edition, 500 pages, September 2017.
[32] E. Dogantekin, M. Yilmaz, A. Dogantekin, E. Avci and A. Sengur, “A robust technique based on invariant moments – ANFIS for recognition of human parasite eggs in microscopic images,” Expert Systems with Applications, vol. 35, pp. 728–738, 2008.
[33] F. Xiang, H. Yong, S. Dandan and Z. Jiexian, “An image retrieval method based on Hu invariant moment and improved annular histogram,” Electronica IR Electro Technica, vol. 20, no. 4, pp. 67-71, 2014.
[34] Y. Sheng and C. Lejeune, “Invariant pattern recognition using Fourier-Mellin transforms and neural networks,” Optics (Paris), vol. 22, no.5, pp. 223-228, 1991.
[35] Y. Liu, Y. Yin and Sh. Zhang, “Hand gesture recognition based on Hu moments in interaction of virtual reality,” 4th International Conference on Intelligent Human-Machine Systems and Cybernetics, IEEE, pp. 145-148, 2012.
[36] M. Abdulrahman, T. R. Gwadabe, F. J. Abdu and A. Eleyan, “Gabor wavelet transform based facial expression recognition sing PCA and LBP,” IEEE, 22nd Signal Processing and Communications Applications Conference. pp. 2265-2268, 2014.
[37] SH. D. Cheng, C. Fang and D. Guangyi, “Facial expression recognition based on Gabor wavelet phase features,” Seventh International Conference on Image and Graphics, pp. 520-523, 2013.
[38] Gh. St-Yves and T. Naselaris. “The feature-weighted receptive field: an interpretable encoding model for complex feature spaces,” NeuroImage. 25 pages, 2017.
[39] V. Kruger, A. Happe and G. Sommer, “Affine real-time face tracking using Gabor wavelet networks,” 15th International Conference on Pattern Recognition, Barcelona, Spain, vol. 1, pp. 127–130, September 2000.
[40] M. A. Hannan, M. Arebey, R. A. Begum, A. Mustafa and H. Basri, “An automated solid waste bin level detection system using Gabor wavelet filters and multi-layer perception,” Resources, Conservation and Recycling, vol. 72, pp. 33– 42, 2013.
[41] U. Raghavendra, U. R. Acharya, H. Fujita, A. Gudigar, J. H. Tan and Sh. Chokkadi, “Application of Gabor wavelet and locality sensitive discriminant analysis for automated identification of breast cancer using digitized mammogram images,” Applied Soft Computing, vol. 46, pp. 151–161, 2016.
[42] A. G. Zuñiga, J. B. Florindo and O. M. Bruno. “Gabor wavelets combined with volumetric fractal dimension applied to texture analysis,” Pattern Recognition Letters. vol. 36, pp. 135-143, 2014.
[43] Q. Chen, J. Luo, P. A. Heng and D. Xia, “Fast and active texture segmentation based on orientation and local variance,” J. Visual Commun. Image Represent, vol. 18, no. 2, pp. 119–129, 2007.
[44] Y. Shi, X. Yang and Y. Guo, “Translation invariant directional Framelet transform combined with Gabor filters for image denoising,” IEEE Trans on Image Processing, vol. 23, no. 1, January. 2014.
[45] A. Vard, A. H. Monadjemi, K. Jamshidi and N. Movahhedinia, “Fast texture energy based image segmentation using directional Walsh–Hadamard transform and parametric active contour models,” Expert Systems with Applications, vol. 38, pp. 11722–11729, 2011.
[46] T. Golonek “Analog circuits testing by means of walsh-hadamard spectrum of supply current transient state monitoring,” Human System Interaction (HSI), The 6th International Conference on.  6-8 June 2013.
[47] R. C. Gonzalez, R. E. Woods and S. L. Eddins, Digital Image Processing using MATLAB, 2nd Edition, 2009.
[48] A. Jain and F. Farrokhnia, “Unsupervised texture segmentation using Gabor filters,” in Proceeding of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 14–19, (Los Angeles, CA, 1990).
[49] K. Beauchamp, Applications of Walsh and Related Functions, London: Academic Press, 1984.
[50] C. Carlet and A. Klapper. “On the arithmetic Walsh coefficients of Boolean functions,” Designs, Codes and Cryptography. vol. 73, no. 2, pp. 299–318, 2014.
[51] A. Monadjemi and P. Moallem, “Texture classification using a novel Walsh/ Hadamard transform,” in 10th WSEAS International Conference on Computers, pp. 1055–1060, (Athens, Greece, 2006).
[52] H. Tahvilian, P. Moallem and A. H. Monadjemi, “Balloon energy based on parametric active contour and directional Walsh–Hadamard transform and its application in tracking of texture object in texture background,” EURASIP Journal on Advances in Signal Processing, vol. 2012, no. 1, pp. 1-15, 2012,
[53] D. B. Palheta, C. E. Guerra, W. F. Sacco and A. A. de M. Meneses, “Automated fracture detection with well logs using global optimization ˮ, Thirteenth International Congress of the Brazilian Geophysical Society, 2013.
[54]  مرتضی خرَم کشکولی و مریم دهقانی. «تشخیص، شناسایی و جداسازی عیب توربین گاز پالایشگاه دوم پارس جنوبی، با استفاده از روش‌های ترکیبی داده‌کاوی، k-means، تحلیل مؤلفه‌های اساسی (PCA) و ماشین بردار پشتیبان (SVM)» مجله مهندسی برق دانشگاه تبریز، جلد 47، شماره 2، تابستان 96.
[55] T. Kohonen, “Essentials of the self-organizing map,” Neural Networks, vol. 37, pp. 52–65, 2013.
[56] J. S. Sengar and N. Sharma, “Review: competitive learning algorithm of neural network,” IJCTA. vol. 2, pp. 1480-1485, 2011.
[57] G. Guojun, M. Chaoqun and W. Jianhong. Data Clustering: Theory, Algorithms, and Applications, SIAM, Cluster analysis, 466 pages, 2008.
[58] H. R. M Shaaban, A. A. Habib and F. A. Obaid, “Performance evaluation of K-Mean and fuzzy C-Mean image segmentation based clustering classifier,” (IJACSA) International Journal of Advanced Computer Science and Applications, Vol. 6, No. 12, 2015.
[59] A. Elazab, Ch. Wang, F. Jia, J. Wu, G. Li and Q. Hu. “Segmentation of brain tissues from magnetic resonance images using adaptively regularized kernel-based fuzzy C-Means clustering,” Computational and Mathematical Methods in Medicine. Volume 2015, Article ID 485495, 12 pages, 2015.
[60] C. M. Christoudias, B. Georgescu and P. Meer. “Synergism in low level vision,” in Proc. IEEE Int. Conf. Pattern Recognit, Quebec, QC, Canada, vol. 4, pp. 150–155, 2002.
[61] غلامرضا اکبری زاده، زینب تیرانداز و سیده مرجان آل سیدغفور. «بخش‌بندی نظارت‌نشده‌ی سلسله مراتبی تصاویر SAR با استفاده از سوپرپیکسل و فشرده‌سازی پراتلاف داده»، مجله‌ی مهندسی برق دانشگاه تبریز، جلد 46، شماره 2، تابستان 1395.

فایل ها

هم رسانی

ارجاع به این مقاله

آمار