بخش بندی پوست چهره مبتنی بر تصاویر رنگی با استفاده از رویکرد ترکیب نگاشت خودسازمان‌ده و شبکه‌های عصبی گازی جهت کاربرد در جراحی‌های پلاستیک چهره

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشکده مهندسی پزشکی، دانشگاه صنعتی سهند، تبریز، ایران

2 داشکده مهندسی پزشکی، دانشگاه صنعتی سهند، تبریز، ایران

چکیده

بخش­بندی تصویر چهره یک مولفه­ی ضروری در کاربردهای پردازش تصویر و بینایی کامپیوتر نظیر شناسایی چهره، شناسایی هویت و آنالیز جراحی پلاستیک چهره است. یکی از مهم­ترین روش­­های بخش­بندی تصاویر چهره،  روش­های مبتنی بر خوشه­بندی هستند. نگاشت خودسازمان­ده (SOM) جزء پرکاربردترین روش مبتنی برشبکه­های عصبی در داده­کاوی است. عیب مهمی که الگوریتم SOM استاندارد دارد این است که ضریب یادگیری در آن وفقی نیست. وفقی بودن ضریب یادگیری در به­روزرسانی وزن­های نگاشت خودسازمان­ده منجر به بهتر شدن عمل­کرد این الگوریتم خواهد شد. شبکه­ی عصبی گازی (NGN) یک یادگیری بدون ناظر بوده که ساختار همسایگی در آن وفقی بوده و وزن سیناپسی مستقل از هر گونه تنظیم توپولوژیکی به­روزرسانی می­شود. هدف اصلی این پژوهش، ارائه­ی روش هیبریدی جدید SOMNGN است که در آن بتوان ضریب یادگیری در فاز تطبیق الگوریتم SOM استاندارد را با استفاده از الگوریتم NGN وفقی کرد. همچنین، دو فضای رنگی شامل YCbCr و فضای نگاشت چهره به­عنوان مرحله­ی پیش­پردازش جهت مدل کردن پوست چهره به­کار گرفته شده است. نتایج به­دست آمده در فضاهای رنگی ذکر شده نشان می­دهند که الگوریتم پیشنهادی نسبت به SOM استاندارد دقت بالاتری در آشکارسازی صحیح پیکسل­های پوست چهره دارد.

کلیدواژه‌ها

عنوان مقاله [English]

Facial Skin Segmentation Based on Color Images using Combined Approach of Self Organizing Map and Neural Gas Network Applicable to Facial Plastic Surgeries

نویسندگان [English]

  • Ali Fahmi Jafargholkhanloo 1
  • Mousa Shamsi 2
1 Faculty of Biomedical Engineering, Sahand University of Technology, Tabriz, Iran
2 Faculty of Biomedical Engineering,, Sahand University of Technology, Tabriz, Iran
چکیده [English]

 Facial image segmentation is an essential component in applications of image processing and computer vision such as face recognition, identity recognition and analysis of facial plastic surgery. The clustering based methods are one of the important methods in the facial image segmentation. Self-Organizing Map (SOM) is a powerful method in the data mining. A main disadvantage of the SOM algorithm is that learning coefficient is not adaptive in this algorithm. Adaptability of learning coefficient in the adaptation phase can improve the performance of the SOM clustering. Neural Gas Network (NGN) is an unsupervised learning that its neighborhood structure is adaptive and synaptic weight is updated without any topological adjustment. The main purpose of this study is to present a new hybrid SOMNGN method in which the learning coefficient is adapted in the adaptation phase of the SOM algorithm using the NGN algorithm. Also, two color spaces, including YCbCr and Face Mapping are used for facial skin modelling as a pre-processing step. Obtained results in the mentioned color spaces show that presented method have the higher accuracy than the standard SOM method.

کلیدواژه‌ها [English]

  • Color Space
  • Clustering
  • Facial Color Images
  • Facial Skin Segmentation
  • Neural Gas Network
  • Self-Organizing Map

مراجع

[1] E. Kaipainen, K. R. Sieber, R. M. Nada, T. J. Maal, C. Katsaros, and P. S. Fudalej, “Regional Facial Asymmetries and Attractiveness of the Face,” European journal of orthodontics, vol. 38, no. 6, pp. 602-608, 2016.
[2] S. Kaya, B. Turk, M. Cankaya, N. Seyhun, and B. U. Coskun, “Assessment of facial analysis measurement by Golden Proportion,” Brazilian journal of otorhinolaryngology, vol. 85, no. 4, pp. 494-501, 2019.
[3] Liu, Y. Y. Fan, A. Samal, and Z. Guo, “Advances in computational facial attractiveness methods,” Multimedia Tools and Applications, vol. 75, no. 23, pp. 16633-16663, 2016.
[4] A. Bakhshali, and M. Shamsi, “Facial Skin Segmentation Using Bacterial Foraging Optimization Algorithm,” Journal of medical signals and sensors, vol. 2, no. 4, pp. 203-210, 2012.
[5] K. Al-Mohair, J. M. Saleh, and S. A. Suandi, “Hybrid human skin detection using neural network and k-means clustering technique,” Applied Soft Computing, vol. 33, pp. 337-347, 2015.
[6] F. Hossain, M. Shamsi, M. R. Alsharif, R. A. Zoroofi, and K. Yamashita, “Automatic Facial Skin Detection Using Gaussian Mixture Model Under Varying Illumination,” International Journal of Innovative Computing, Information and Control, vol. 8, no. 2, pp. 1135-1144, 2012.
[7] Shamsi, R. A. Zoroofi, C. Lucas, M. S. Hasanabadi, and M. R. Alsharif, “Automatic Facial Skin Segmentation Based on EM Algorithm under Varying Illumination,” IEICE transactions on information and systems, vol. 91, no. 5, pp. 1543-1551, 2008.
[8] Cuevas, D. Zaldivar, M. Perez, and E. N. Sanchez, “LVQ Neural Networks Applied To Face Segmentation,” Intelligent Automation & Soft Computing, vol. 15, no. 3, pp. 439-450, 2009.
[9] A. Naji, R. Zainuddin, and H. A. Jalab, “Skin segmentation based on pixel color clustering models,” Digital Signal Processing, vol. 22, no. 6, pp. 933-940, 2012.
[10] Khan, A. Hanbury, J. Stottinger, and A. Bais, “Color based skin classification,” Pattern Recognition Letters, vol. 32, no. 2, pp. 157-163, 2012.
[11] A. Bakhshali, and M. Shamsi, “Segmentation of color lip images by optimal thresholding using bacterial foraging optimization (BFO),” Journal of Computational Science, vol. 5, no. 2, pp. 251-257, 2014.
[12] Hajiarbabi, and A. Agah, “Human Skin Detection in Color
Images Using Deep Learning,” International Journal of Computer Vision and Image Processing, vol. 5, no. 2, pp. 1-13, 2015.
[13] A. Pujol, M. Pujol, A. J. Morenilla, and M. J. Pujol, “Face Detection Based on Skin Color Segmentation Using Fuzzy Entropy,” Entropy, vol. 19, no. 1, pp.1-22, 2017.
[14] Xu, C. Guo, Y. Hu, H. Lu, X. Li, F. Li, and W. Zhang, “Automatic Facial Complexion Classification Based on Mixture Model,” Pacific Rim Conference on Multimedia. Springer, Cham, pp. 327-336, 2017.
[15] Y. Kwon, and S. I. Chien, “Adaptive Skin Color Detection through Iterative Illuminant Color Estimation and Conversion for Preferred Skin Color Reproduction,” Molecular Crystals and Liquid Crystals, vol. 677, no. 1, pp. 105-117, 2018.
[16] Paracchini, M. Marcon, F. Villa, and S. Tubaro, “Deep skin detection on low resolution grayscale images,” Pattern Recognition Letters, vol. 131, pp. 322-328, 2020.
[17] Kumar, M. Alshehri, R. AlGhamdi, P. Sharma, and V. Deep, “A DE-ANN Inspired Skin Cancer Detection Approach Using Fuzzy C-Means Clustering,” Mobile Networks and Applications, vol. 25, pp. 1319-1329, 2020.
[18] B. Salah, M. Othmani, and M. Khrallah, “A novel approach for human skin detection using convolutional neural
network,” The Visual Computer, pp. 1-11, 2021.
[19] M. Aibinu, A. A. Shafie, and M. J. E. Salami, “Performance Analysis of ANN based YCbCr Skin Detection Algorithm,” Procedia Engineering, vol. 41, pp. 1183-1189, 2012.
[20] Sarifuddin, and R. Missaoui, “A New Perceptually Uniform Color Space with Associated Color Similarity Measure for Content-Based Image and Video Retrieval,” Proc. of ACM SIGIR workshop on multimedia information retrieval, pp. 1-8, 2005.
[21] Mohanty, and M. V. Raghunadh, “A New Approach to Face Detection based on YCgCr Color Model and Improved AdaBoost Algorithm,” International Conference on Communication and Signal Processing (ICCSP). IEEE, pp. 1392-1396, 2016.
[22] Roterman, and M. Porat, “Progressive image coding using regional color correlation,” 4th EURASIP Conference focused on Video/Image Processing and Multimedia Communications. IEEE, vol.1, pp .65-70, 2003.
[23] D. Cheng, X. H. Jiang, Y. Sun, and J. Wang, “Color image segmentation: advances and prospects,” Pattern recognition, vol. 34, no. 12, pp. 2259-2281, 2001.
[24] Ford, and A. Roberts, “Colour Space Conversions,” Westminster University, London, pp. 1-31, 1998.
[25] Kotsarenko, and F. Ramos, “Measuring perceived color difference using YIQ NTSC transmission color space in mobile applications,” Programacion Matematica y Software, vol. 2, no. 2, pp. 27-43, 2010.
[26] Saber, and A. M. Tekalp, “Frontal-view face detection and facial feature extraction using color, shape and symmetry based cost functions,” Pattern Recognition Letters, vol. 19, no. 8, pp. 669-680, 1998.
[27] Prema, and D. Manimegalai, “Survey on skin tone detection using color spaces,” International Journal of Applied Information Systems, vol. 2, no. 2, pp. 18-26, 2012.
[28] Y. Kahu, R. B. Raut, and K. M. Bhurchandi, “Review and evaluation of color spaces for image/video compression,” Color Research & Application, vol. 44, no. 1, pp. 8-33, 2019.
[29] M. C. Gonzalez, M. A. V. Rodriguez, and J. A. G. Pulido, “Detection skin in face recognition systems: A colour spaces study,” Digital Signal Processing, vol. 20, no. 3, pp. 806-823, 2010.
[30] A. M. Riveros, B. A. C. Espitia, L. E. A. Pico, “Comparison between K-means and Self-Organizing Maps algorithms used for diagnosis spinal column patients,” Informatics in Medicine Unlocked, vol. 16, pp. 1-11, 2019.
[31] Mishra, and M. Panda, “Medical image retrieval using self-organising map on texture features,” Future Computing and Informatics Journal, vol. 3, no. 2, pp. 359-370, 2018.
[32] Wang, X. Liu, N. Q. Soomro, G. Han, and W. Liu, “Content-sensitive superpixel segmentation via self-organization-map neural network,” Journal of Visual Communication and Image Representation, vol. 63, pp. 1-10, 2019.
[33] Martinetz, and K. Schulten, “A Neural Gas Network Learns Topologies,” Artificial Neural Networks, pp. 397-402, 1991.
[34] L. Du, “Clustering a neural network approach,” Neural networks, vol. 23, no. 1, pp. 89-107, 2010.
[35] Hagenauer, and M. Helbich, “Contextual neural gas for spatial clustering and analysis,” International Journal of Geographical Information Science, vol. 27, no. 3, pp. 251-266, 2013.
[36] D. Luptakova, M. Simon, L. Huraj, and J. Pospichal, “Neural Gas Clustering Adapted for Given Size of Clusters,” Mathematical Problems in Engineering, pp. 1-7, 2016.
[37] A. Bakhshali, M. Shamsi, and M. Sadeghi, “Evaluation of facial soft tissue parameters for Northwestern students in Iran,” Journal of Craniomaxillofacial Research, vol. 2, no. 1-2, pp. 78-82, 2015.
[38] Elazab, C. 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, pp. 1-13, 2015.
[39] Kohonen, “The Self-organizing Map,” Proceedings of the IEEE, vol. 78, no. 9, pp. 1464-1480, 1990.
[40] Tesauro, D. S. Touretzky, and T. K. Leen, “A Growing Neural Gas Network Learns Topologies,” Advances in neural information processing systems, pp. 625-632, 1995.
[41] L. Fred, S.N. Kumar, P. Padmanaban, B. Gulyas, and H.A. Kumar, “Fuzzy-crow search optimization for medical image segmentation,” In Applications of Hybrid Metaheuristic Algorithms for Image Processing, pp. 413-439, 2020.
[42] Verma, D. Verma D, and P.K. Tiwari, “A population based hybrid FCM-PSO algorithm for clustering analysis and segmentation of brain image,” Expert Systems with Applications, 2020.

فایل ها

هم رسانی

ارجاع به این مقاله

آمار