Deep Scattering Convolutional Network for Cosmetic Skin Classification

  IJETT-book-cover  International Journal of Engineering Trends and Technology (IJETT)          
  
© 2022 by IJETT Journal
Volume-70 Issue-7
Year of Publication : 2022
Authors : Shwetambari Borade, Dhananjay Kalbande, Kristen Pereira, Rushil Patel, Sudhanshu Kulkarni
DOI : 10.14445/22315381/IJETT-V70I7P202

How to Cite?

Shwetambari Borade, Dhananjay Kalbande, Kristen Pereira, Rushil Patel, Sudhanshu Kulkarni, "Deep Scattering Convolutional Network for Cosmetic Skin Classification" International Journal of Engineering Trends and Technology, vol. 70, no. 7, pp. 10-23, 2022. Crossref, https://doi.org/10.14445/22315381/IJETT-V70I7P202

Abstract
The use of computer-based solutions or artificial intelligence in detecting face skin conditions has progressed considerably over the years. Combining cosmetic skin care concepts with technical advancements has shown noble outputs. In recent times, deep convolutional neural networks have been applied for image classification applications in various domains like healthcare, identification of objects in various aspects, control systems, machine visions, etc., and have shown remarkable results. The scattering network is commonly and consistently utilized on the initial layers of a supervised mixed convolutional model. This study demonstrates that layers in the first layer do not always have to be learned, with pre-defined models attaining the greatest performance to date when competing with Deep CNNs. ResNETs, in particular, have been adopted widely because they can solve the vanishing gradient problem that prevails in most deep networks. So, they have exploited the capacity of wavelet transforms, Scattering Networks, and the Residual Networks model for image classification to identify cosmetic skin problems like oily or dry skin. According to results obtained and statistical assessments, the ResNet model and Scattering Networks have the greatest validation accuracy of 98 percent for image classification of oily and dry skin pictures. They have also compared the model with others where scattering networks for SVM have an accuracy of 57 percent, whereas VGG16 gave an accuracy of 95.9 percent on validation sets. And DWT with ANN has an accuracy of 63.2 percent, and Gabor filters and support vector machine have the lowest accuracy of 48.8 percent.

Keywords
Deep Learning, Histogram Equalization, ResNet, Skin Classification, Wavelet Scattering.

Reference
[1] S. Kolkur, D. Kalbande, P. Shimpi, C. Bapat, and J. Jatakia, “Human Skin Detection Using RGB, HSV and YCbCr Color Models,” vol. 137, pp. 324–332, 2017, doi: 10.2991/iccasp-16.2017.51.
[2] D. Kalbande, Nikhil Barhate, Parth R. Dedhia, Arnab Ghorai, Darshan Savalia, Dr.Uday Khopkar, “AI Enabled Method for predicting Acne-Non Acne.” National Conference on Artificial Intelligence in Health Informatics & Virtual Reality, 2019.
[3] P. M. Arabi, G. Joshi, R. N. Reddy, A. S. R, and A. P. S, “Categorising Normal Skin, Oily Skin and Dry Skin using 4-Connectivity and 8-Connectivity Region Properties,” Int. J. Adv. Netw. Appl., vol. 4, no. 4, pp. 2016–2018, 2017, [Online]. Available: http://www.ijana.in/Special Issue/A4.pdf.
[4] L. Baumann, “Understanding and Treating Various Skin Types: The Baumann Skin Type Indicator,” Dermatol. Clin., vol. 26, no. 3, pp. 359–373, 2008, doi: 10.1016/j.det.2008.03.007.
[5] M. I. Razzak, S. Naz, and A. Zaib, “Deep learning for medical image processing: Overview, challenges and the future,” Lect. Notes Comput. Vis. Biomech., vol. 26, pp. 323–350, 2018, doi: 10.1007/978-3-319-65981-7_12.
[6] A. Anton, N. F. Nissa, A. Janiati, N. Cahya, and P. Astuti, “Application of Deep Learning Using Convolutional Neural Network (CNN) Method For Women’s Skin Classification,” Sci. J. Informatics, vol. 8, no. 1, 2021, doi: 10.15294/sji.v8i1.26888.
[7] Indriyani and I. Made Sudarma, “Classification of facial skin type using discrete wavelet transform, contrast, local binary pattern and support vector machine,” J. Theor. Appl. Inf. Technol., vol. 98, no. 5, 2020.
[8] T. J. Jebaseeli, D. J. David, and R. Venkatesan, “Prediction of COVID’19 through multiple organ analysis using iot devices and machine learning techniques,” Int. J. Eng. Trends Technol., vol. 69, no. 8, 2021, doi: 10.14445/22315381/IJETT-V69I8P213.
[9] R. D. Amelia, I. I. Tritoasmoro, and N. Ibrahim, “Klasifikasi Jenis Kulit Wajah Menggunakan Metode Discrete Wavelet Transform dan Backpropagation,” e-Proceeding Eng., vol. 6, no. 2, 2019.
[10] M. Thanjaivadivel and R. Suguna, “Leaf disease prediction using fast enhanced learning method,” Int. J. Eng. Trends Technol., vol. 69, no. 9, 2021, doi: 10.14445/22315381/IJETT-V69I9P205.
[11] E. Oyallon et al., “Scattering Networks for Hybrid Representation Learning,” IEEE Trans. Pattern Anal. Mach. Intell., 2018, doi: 10.1109/TPAMI.2018.2855738.
[12] P. Singh, G. Saha, and M. Sahidullah, “Deep scattering network for speech emotion recognition,” Eur. Signal Process. Conf., vol. 2021-August, pp. 131–135, 2021, doi: 10.23919/EUSIPCO54536.2021.9615958.
[13] J. Shi, Y. Zhao, W. Xiang, V. Monga, X. Liu, and R. Tao, “Deep Scattering Network with Fractional Wavelet Transform,” IEEE Trans. Signal Process., 2021, doi: 10.1109/TSP.2021.3098936.
[14] T. Ki and Y. Hur, “Deep Scattering Network with Max-Pooling,” in Data Compression Conference Proceedings, 2021, vol. 2021- March, doi: 10.1109/DCC50243.2021.00052.
[15] T. Karim et al., “Cnn applied in public transport for the protection against the covid-19 spread,” Int. J. Eng. Trends Technol., vol. 69, no. 10, 2021, doi: 10.14445/22315381/IJETT-V69I10P205.
[16] C. Dev et al., “Diagnostic Quality Assessment of Ocular Fundus Photographs: Efficacy of Structure-Preserving ScatNet Features,” in Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, 2019, doi: 10.1109/EMBC.2019.8857046.
[17] V. R. Surendra and M. Zawodniok, “Distributed beamforming using a scattering network,” in CNSR 2010 - Proceedings of the 8th Annual Conference on Communication Networks and Services Research, 2010, doi: 10.1109/CNSR.2010.61.
[18] S. Srivastava, A. Nigam, and M. Muthaiyan, “Low-cost Driver Assistance System for drivers suffering from Dyslexia or Colorblindness using Machine Learning,” Int. J. Eng. Trends Technol., vol. 69, no. 12, 2021, doi: 10.14445/22315381/IJETT-V69I12P207.
[19] A. Singh and N. Kingsbury, “Dual-Tree wavelet scattering network with parametric log transformation for object classification,” in ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, 2017, doi: 10.1109/ICASSP.2017.7952631.
[20] P. Kulkarni, J. Sadasivan, A. Adiga, and C. S. Seelamantula, “Epoch Estimation from a Speech Signal Using Gammatone Wavelets in a Scattering Network,” in ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, 2020, vol. 2020-May, doi: 10.1109/ICASSP40776.2020.9052986.
[21] S. Minaee and Y. Wang, “Fingerprint recognition using translation invariant scattering network,” in 2015 IEEE Signal Processing in Medicine and Biology Symposium - Proceedings, 2016, doi: 10.1109/SPMB.2015.7405471.
[22] L. Liu, J. Wu, D. Li, L. Senhadji, and H. Shu, “Fractional wavelet scattering network and applications,” IEEE Trans. Biomed. Eng., vol. 66, no. 2, 2019, doi: 10.1109/TBME.2018.2850356.
[23] B. H. Li, J. Zhang, and W. S. Zheng, “HEp-2 cells staining patterns classification via wavelet scattering network and random forest,” in Proceedings - 3rd IAPR Asian Conference on Pattern Recognition, ACPR 2015, 2016, doi: 10.1109/ACPR.2015.7486535.
[24] S. R. Manne, S. Bin Bashar, K. K. Vupparaboina, J. Chhablani, and S. Jana, “Improved Fundus Image Quality Assessment: Augmenting Traditional Features with Structure Preserving ScatNet Features in Multicolor Space,” in Proceedings - 2020 IEEE EMBS Conference on Biomedical Engineering and Sciences, IECBES 2020, 2021, doi: 10.1109/IECBES48179.2021.9398757.
[25] H. F. Yang, B. Y. Lin, K. Y. Chang, and C. S. Chen, “Joint estimation of age and expression by combining scattering and convolutional networks,” ACM Trans. Multimed. Comput. Commun. Appl., vol. 14, no. 1, 2018, doi: 10.1145/3152118.
[26] E. Ortega-Espinoza, M. Flores-Cruz, D. C. Loayza, J. Velarde-Cuadros, A. Delgado, and E. L. Huamaní, “Use of Machine Learning to Predict the Occurrence of Deaths in the Departments Most Affected by Covid-19 in Peru,” Int. J. Eng. Trends Technol., vol. 70, no. 3, 2022, doi: 10.14445/22315381/IJETT-V70I3P206.
[27] J. Gao, L. Jiao, F. Liu, S. Yang, B. Hou, and X. Liu, “Multiscale Curvelet Scattering Network,” IEEE Trans. Neural Networks Learn. Syst., 2021, doi: 10.1109/TNNLS.2021.3118221.
[28] A. Malhotra, A. Sankaran, M. Vatsa, and R. Singh, “On Matching Finger-Selfies Using Deep Scattering Networks,” IEEE Trans. Biometrics, Behav. Identity Sci., vol. 2, no. 4, 2020, doi: 10.1109/TBIOM.2020.2999850.
[29] A. Sankaran, A. Malhotra, A. Mittal, M. Vatsa, and R. Singh, “On smartphone camera-based finger photo authentication,” in 2015 IEEE 7th International Conference on Biometrics Theory, Applications, and Systems, BTAS 2015, 2015, doi: 10.1109/BTAS.2015.7358782.
[30] S. Minaee and Y. Wang, “Palmprint recognition using deep scattering network,” in Proceedings - IEEE International Symposium on Circuits and Systems, 2017, doi: 10.1109/ISCAS.2017.8050421.
[31] S. K. Bandyopadhyay, P. Bose, A. Bhaumik, and S. Poddar, “Machine Learning and Deep Learning Integration for Skin Diseases Prediction,” Int. J. Eng. Trends Technol., vol. 70, no. 2, 2022, doi: 10.14445/22315381/IJETT-V70I2P202.
[32] L. Liang, D. Xie, J. Xu, M. Li, L. Lin, and L. Jin, “Region-aware scattering convolution networks for facial beauty prediction,” in Proceedings - International Conference on Image Processing, ICIP, 2018, vol. 2017-September, doi: 10.1109/ICIP.2017.8296805.
[33] E. Oyallon, E. Belilovsky, and S. Zagoruyko, “Scaling the Scattering Transform: Deep Hybrid Networks,” in Proceedings of the IEEE International Conference on Computer Vision, 2017, vol. 2017-October, doi: 10.1109/ICCV.2017.599.
[34] V. Kinakh, O. Taran, and S. Voloshynovskiy, “ScatSimCLR: Self-supervised contrastive learning with pretext task regularization for small-scale datasets,” in Proceedings of the IEEE International Conference on Computer Vision, 2021, vol. 2021-October, doi: 10.1109/ICCVW54120.2021.00129.
[35] J. B. Regli and J. D. B. Nelson, “Scattering convolutional hidden Markov trees,” in Proceedings - International Conference on Image Processing, ICIP, 2016, vol. 2016-August, doi: 10.1109/ICIP.2016.7532685.
[36] R. Balestriero and H. Glotin, “Scattering Decomposition for Massive Signal Classification: From Theory to Fast Algorithm and Implementation with Validation on International Bioacoustic Benchmark,” in Proceedings - 15th IEEE International Conference on Data Mining Workshop, ICDMW 2015, 2016, doi: 10.1109/ICDMW.2015.127.
[37] Yulianto, Nurhasanah, R. Yulistiani, and G. P. Kusuma, “Face Image Super-Resolution Using Combination of Max-Feature-Map and CMU-Net to Enhance Low-Resolution Face Recognition,” Int. J. Eng. Trends Technol., vol. 70, no. 3, 2022, doi: 10.14445/22315381/IJETT-V70I3P201.
[38] M. Li et al., “Skeleton Graph Scattering Networks for 3D Skeleton-based Human Motion Prediction,” in Proceedings of the IEEE International Conference on Computer Vision, 2021, vol. 2021-October, doi: 10.1109/ICCVW54120.2021.00101.
[39] H. Y. Feng, P. Y. Chen, and J. Hou, “SR-ScatNet Algorithm for On-device ECG Time Series Anomaly Detection,” in Conference Proceedings - IEEE SOUTHEASTCON, 2021, vol. 2021-March, doi: 10.1109/SoutheastCon45413.2021.9401872.
[40] P. Birajadar, M. Haria, S. G. Sangodkar, and V. Gadre, “Unconstrained Ear Recognition Using Deep Scattering Wavelet Network,” in 2019 IEEE Bombay Section Signature Conference, IBSSC 2019, 2019, vol. 2019January, doi: 10.1109/IBSSC47189.2019.8973055.
[41] H. Zhou et al., “Weight-Variable Scattering Convolution Networks and Its Application in Electromagnetic Signal Classification,” IEEE Access, vol. 7, 2019, doi: 10.1109/ACCESS.2019.2957519.
[42] M. Vashisht and B. Kumar, “A Survey Paper on Object Detection Methods in Image Processing,” 2020 Int. Conf. Comput. Sci. Eng. Appl. ICCSEA 2020, pp. 5–8, 2020, doi: 10.1109/ICCSEA49143.2020.9132871.
[43] X. Shen, J. Zhang, C. Yan, and H. Zhou, “An Automatic Diagnosis Method of Facial Acne Vulgaris Based on Convolutional Neural Network,” Sci. Rep., vol. 8, no. 1, 2018, doi: 10.1038/s41598-018-24204-6.
[44] N. Hameed, A. M. Shabut, M. K. Ghosh, and M. A. Hossain, “Multiclass multi-level classification algorithm for skin lesions classification using machine learning techniques,” Expert Syst. Appl., vol. 141, 2020, doi: 10.1016/j.eswa.2019.112961.
[45] A. Singhal, R. Shukla, P. K. Kankar, S. Dubey, S. Singh, and R. B. Pachori, “Comparing the capabilities of transfer learning models to detect skin lesion in humans,” Proc. Inst. Mech. Eng. Part H J. Eng. Med., vol. 234, no. 10, 2020, doi: 10.1177/0954411920939829.
[46] G. George, R. M. Oommen, S. Shelly, S. S. Philipose, and A. M. Varghese, “A Survey on Various Median Filtering Techniques For Removal of Impulse Noise From Digital Image,” in Proc. IEEE Conference on Emerging Devices and Smart Systems, ICEDSS 2018, 2018, doi: 10.1109/ICEDSS.2018.8544273.
[47] T. Chen and H. R. Wu, “Adaptive impulse detection using center-weighted median filters,” IEEE Signal Process. Lett., vol. 8, no. 1, 2001, doi: 10.1109/97.889633.
[48] S. Patel, K. P. Bharath, S. Balaji, and R. K. Muthu, “Comparative Study on Histogram Equalization Techniques for Medical Image Enhancement,” in Advances in Intelligent Systems and Computing, 2020, vol. 1048, doi: 10.1007/978-981-15-0035-0_54.
[49] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2016, vol. 2016-December, doi: 10.1109/CVPR.2016.90.
[50] S. Borade and D. Kalbande, “Survey paper based critical reviews for Cosmetic Skin Diseases,” in Proceedings - International Conference on Artificial Intelligence and Smart Systems, ICAIS 2021, 2021, doi: 10.1109/ICAIS50930.2021.9395803