آشکارسازی صورت با استفاده از فیلترهای گابور و شبکههای عصبی
محورهای موضوعی : مهندسی برق و کامپیوترمحمود محلوجی 1 , رضا محمدیان 2 *
1 - دانشگاه آزاد اسلامی، واحد كاشان
2 - دانشگاه آزاد اسلامی، واحد كاشان
کلید واژه: آشکارسازی صورت شبکه عصبی فیلتر گابور ویژگیهای گابور,
چکیده مقاله :
در این مقاله، روشی قدرتمند برای آشکارسازی صورت از زوایای مختلف با استفاده از ترکیب فیلترهای گابور و شبکه عصبی بیان میشود. در ابتدا رابطه ریاضی تولید فیلتر گابور مورد بررسی قرار میگیرد و در مرحله بعد با بررسی 75 بانک فیلتر مختلف، محدوده مقادیر پارامترهای مؤثر در تولید فیلتر گابور مشخص شده و سپس بهترین مقدار برای آنها به دست میآید. شبکه عصبی مورد استفاده در این مقاله از نوع پیشخور با روش بازگشتی است و بردار ورودی این شبکه عصبی از کانوالو تصویر با تنها یک فیلتر گابور با زاویه 2/ و فرکانس 2/ در حوزه فرکانس به دست میآید. الگوریتم پشنهادی در این مقاله روی 550 تصویر از 2 پایگاه تصویر فرت با پسزمینه ساده و مارکوس وبر با پسزمینه پیچیده آزمایش شده و دقت آشکارسازی آن به ترتیب 4/98% و 95% است. همچنین به کمک الگوریتم ویولا جونز ناحیه صورت را در 550 نمونه تصویر به دست آورده و مقایسهای بین نتایج به دست آمده از الگوریتم ویولاجونز و الگوریتم پیشنهادی آورده میشود.
In this paper, a robust method for face detection from different views using a combination of Gabor filters and neural networks is presented. First, a mathematical equation of Gabor filter is expressed. Then, by examining 75 different filter banks, range of effective parameters values in Gabor filter generation is determined, and finally, the best value for them is specified. The neural network used in this paper is a feed-forward back-propagation multilayer perceptron network. The input vector of the neural network is obtained from the convolution the input image and a Gabor filter with angles π / 2 and the frequency π / 2 in the frequency domain. The proposed method has been tested on 550 image samples from Feret database with simple background and Markus Weber database with complex background, and detection accuracy of them is 98.4% and95%, respectively. Also, the face area has been detected using Viola-Jones algorithm, and then comparison between the results obtained from Viola-Jones algorithm and the proposed method is described.
[1] L. Ismail, "Face detection technique of Humanoid Robot NAO for application in robotic assistive therapy," in Proc. IEEE Int. Conf. on Control System, Computing, and Engineering, ICCSCE'11, pp. 517-521, Nov. 2011.
[2] R. Sarkara, S. Bakshib, and P. Sac, "A real-time model for multiple human face tracking from low-resolution surveillance videos," Procedia Technology, vol. 6, pp. 1004-1010, 2012.
[3] L. Xiaohua, K. Lam, S. Lansun, and Z. Jiliu, "Face detection using simplified Gabor features and hierarchical regions in a cascade of classifiers," Pattern Recognition Letters, vol. 8, no. 1, pp. 717-728, Jun. 2009.
[4] K. Hawari, B. Ghazali, J. Ma, R. Xiao, and S. Aryza Lubis, "An innovative face detection based on YCgCr color space," Physics Procedia, 2012.
[5] W. Yang and J. Hongmei, "Face detection based on template matching and 2DPCA algorithm," in Proc. Congress on Image and Signal Processing, CISP'08, vol. 4, pp. 575-579, May 2008.
[6] D. Jin and S. Lin, Advances in Mechanical and Electronic Engineering, vol. 2, Springer, 2012.
[7] R. Dhanabal, "Gabor filter design for fingerprint application using MATLAB and verilog HDL," Int. J. of Engineering and Technology, vol. 5, no. 2, pp. 1386-139, Apr. 2013.
[8] R. Samad and H. Sawada, "Edge-based facial feature extraction using Gabor wavelet and convolution filters," in Prof. Conf. on Machine Vision Applications, pp. 430-433, 2011.
[9] A. Bianconi and F. Fernandez, "Evaluation of the effects of Gabor filter parameters on texture classification," Pattern Recognition, vol. 40, no. 12, pp. 3325-3335, Dec. 2007.
[10] A. Serrano, I. Martin de Diego, C. Conde, and E. Cabello, "Analysis of variance of Gabor filter banks parameters for optimal face recognition," Pattern Recognition Letters, vol. 32, no. 15, pp. 1998-2008, Nov. 2011.
[11] A. Bhuiyan and C. H. Liu, "On face recognition using Gabor filters," Int. J. of Computer, Electrical, Automation, Control and Information Engineering, vol. 1, no. 4, pp. 856-861, 2007.
[12] D. Verma, V. Dhaka, and S. Agrwal, "An improved average Gabor wavelet filter feature ectraction technique for facial expression recognition," Int. J. of Innovations in Engineering and Technology, vol. 2, no. 4, pp. 35-41, Aug. 2013.
[13] L. Huang, A. Shimizu, and H. Kobatake, "Robust face detection using Gabor filter features," Pattern Recognition Letters, vol. 26, no. 11, pp. 1641-1649, Aug. 2005.
[14] H. Sahoolizadeh, D. Sarikhanimoghadam, and H. Dehghani, "Face detection using Gabor wavelets and neural networks," World Academy of Science, Engineering, and Technology, vol. 2, no. 9, pp. 456-458, 2008.
[15] Z. Sun, G. Bebis, and R. Miller, "On - road vehicle detection using evolutionary Gabor filter optimization," IEEE Trans. on Intelligent Transportation Systems, vol. 6, no. 2, pp. 125-137, Jun. 2005.
[16] A. Sahu and S. Prakash, "Face detection by fine tuning the Gabor filter parameter," Int. J. of Computer Science and Information Technologies, vol. 2, no. 6, pp. 2719-2724, Nov./Dec. 2011.
[17] Feret Database, Available FTP: http://www.nist.gov/itl/iad/ig/colorferet.cfm.
[18] Markus Weber Database, Available FTP: http://www.vision.caltech.edu/Image_Datasets/faces/faces.tar.
[19] P. Viola and M. Jones, "Robust real-time object detection," in Proc. 2nd Int. Workshop on Statistical and Computational Theories of Vision - Modeling Learning, Computing, and Sampling, pp. 1-25, Jul. 2001.
[20] A. Movellan, Tutorial on Gabor filter [Online], Available: http://mplab.ucsd.edu/wordpress/?page_id=75, 2008.
[21] J. Oh and S. Choi, "Selective generation of Gabor features for fast face recognition on mobile devices," Pattern Recognition Letters, vol. 34, no. 13, pp. 1540-1547, Oct. 2013.
[22] V. Shiv, N. Prasad, and J. Domke, Gabor Filter Visualization, Technical Report, Maryland, 2005.
[23] A. Palmer and J. Jones, "An evaluation of the two-dimensional Gabor filter model of simple receptive fields in cat striate cortex," J. of Neuro Physiology, vol. 58, no. 6, pp. 1233-1258, 1987.
[24] P. Kruizinga, N. Petkov, and S. E. Grigorescu, "Comparison of texture features based on Gabor filters," in Proc. of the 10th Int. Conf. on Image Analysis and Processing, vol. 1, pp. 142-147, Sep. 1999.
[25] W. Cheng Xiang, V. Venkatesh, and D. HaiLin, "Facial expression recognition using radia lencoding of local Gabor features and classifier synthesis," Pattern Recognition, vol. 45, no. 1, pp. 80-91, 2012.
[26] N. Petkov, "2D Gabor functions and filters for image processing and computer vision," University of Groningen, 2007.
[27] L. Roger and J. Easton, Fourier Methods in Imaging, Rochester: John Wiley and Sons, Ltd, 2010.
[28] G. Amayeh, A. Tavakkoli, and G. Bebis, "Accurate and efficient computation of Gabor features in real-time applications," Lecture Note in Computer Scinc, 2009.
[29] N. Boulgouris, V. Konstantinos, N. Plataniotis, and E. Tzanakou, Biometrics: Theory, Methods, and Applications, John Wiley & Sons, 2009.
[30] S. Meshgini, , and H. Seyedarabi,"Face recognition using Gabor-based direct linear discriminant analysis and support vector machine," Computers and Electrical Engineering, vol. 39, no. 3, pp. 727-745, Apr. 2013.