Skin Identification Using Deep Convolutional Neural Network
Skin identification can be used in several security applications such as border’s security checkpoints and facial recognition in bio-metric systems. Traditional skin identification techniques were unable to deal with the high complexity and uncertainty of human skin in uncontrolled environments. To address this gap, this research proposes a new skin identification technique using deep convolutional neural network. The proposed sequential deep model consists of three blocks of convolutional layers, followed by a series of fully connected layers, optimized to maximize skin texture classification accuracy. The proposed model performance has been compared with some of the well-known texture-based skin identification techniques and delivered superior results in terms of overall accuracy. The experiments were carried out over two datasets including FSD Benchmark dataset as well as an in-house skin texture patch dataset. Results show that the proposed deep skin identification model with highest reported accuracy of 0.932 and minimum loss of 0.224 delivers reliable and robust skin identification.
KeywordsSkin texture analysis Convolutional Neural Networks Deep learning Segmentation
This research is supported by the MIDAS project (agreement G5381), under the NATO Science for Peace and Security Programme. The Titan X Pascal GPU used for this research was donated by NVIDIA.
- 1.Bae, H.J., Jung, S.H.: Image retrieval using texture based on DCT. In: Proceedings of 1997 International Conference on Information, Communications and Signal Processing, ICICS 1997, vol. 2, pp. 1065–1068. IEEE (1997)Google Scholar
- 3.Chaichulee, S., et al.: Multi-task convolutional neural network for patient detection and skin segmentation in continuous non-contact vital sign monitoring. In: 2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017), pp. 266–272. IEEE (2017)Google Scholar
- 4.Du, S.S., Zhai, X., Poczos, B., Singh, A.: Gradient descent provably optimizes over-parameterized neural networks. arXiv preprint arXiv:1810.02054 (2018)
- 8.Lloyd, K., Marshall, D., Moore, S.C., Rosin, P.L.: Detecting violent crowds using temporal analysis of GLCM texture. arXiv preprint arXiv 1605 (2016)Google Scholar
- 9.Mahmoud, M.K.A., Al-Jumaily, A.: A hybrid system for skin lesion detection: based on Gabor wavelet and support vector machine. In: Information Technology: Proceedings of the 2014 International Symposium on Information Technology (ISIT 2014), Dalian, China, 14–16 October 2014, p. 39. CRC Press (2015)Google Scholar
- 14.Raupov, D.S., Myakinin, O.O., Bratchenko, I.A., Zakharov, V.P., Khramov, A.G.: Skin cancer texture analysis of OCT images based on Haralick, fractal dimension, Markov random field features, and the complex directional field features. In: Optics in Health Care and Biomedical Optics VII, vol. 10024, p. 100244I. International Society for Optics and Photonics (2016)Google Scholar
- 16.Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
- 17.Sun, Y., Tistarelli, M., Maltoni, D.: Structural similarity based image quality map for face recognition across plastic surgery. In: 2013 IEEE Sixth International Conference on Biometrics: Theory, Applications and Systems (BTAS), pp. 1–8. IEEE (2013)Google Scholar
- 18.Torkashvand, F., Fartash, M.: Automatic segmentation of skin lesion using Markov random field. Can. J. Basic Appl. Sci. 3(3), 93–107 (2015)Google Scholar
- 19.Yaghoubyan, S.H., Maarof, M.A., Zainal, A., Foâ, M., Oghaz, M.M., et al.: Fast and effective bag-of-visual-word model to pornographic images recognition using the freak descriptor. J. Soft Comput. Decis. Support Syst. 2(6), 27–33 (2015)Google Scholar
- 21.Zhang, X., Weng, C., Yu, B., Li, H.: In-vivo differentiation of photo-aged epidermis skin by texture-based classification. In: Optics in Health Care and Biomedical Optics VI, vol. 9268, p. 92682G. International Society for Optics and Photonics (2014)Google Scholar