A NOVEL COLOR-BASED FEATURE EXTRACTION METHOD FOR SVM BASED SKIN SEGMENTATION

Abstract

The colored digital images can be represented in different color spaces. The most used color space is Red-Green-Blue space. However, this space can be transformed to Luminance-Blue Difference-Red Difference space for extraction of light intensity information and Hue-Saturation-Value space. The defined features of color pixels give strong information about whether they belong to a human skin or not. In this paper, a novel color-based feature extraction method is proposed, which use both red, green, blue, luminance, hue and saturation information. The proposed method is applied on an image database consists of various people with diverse age, racial and gender characteristics. The obtained features are used to segment the human skin by using Support-Vector- Machine algorithm and finally the promising performance results are presented comparatively with the most-common methods in the literature.

Keywords

• Feature extraction
• Image segmentation
• Support Vector Machine

References

1. Zarit BD, Super BJ, Quek FKH. Comparison of Five Color Models in Skin Pixel Classification. In: ICCV'99, 1999; doi: 10.1109/RATFG.1999.799224.
2. Chakraborty BK, Bhuyan MK, Image specific discriminative feature extraction for skin segmentation. Multimedia Tools and Applications 2020; doi: 10.1007/s11042-020-08762-4.
3. Topiwala A, Al-Zogbi L, Fleiter T, Krieger A. Adaptation and Evaluation of Deep Learning Techniques for Skin Segmentation on Novel Abdominal Dataset. In: IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE); 2019.
4. Sadik F, Subah MR, Dastider AG, Moon SA, Ahbab SS, Fattah SA. Bangla Sign Language Recognition with Skin Segmentation and Binary Masking. In: 5th IEEE International WIE Conference on Electrical and Computer Engineering (WIECON-ECE); 2019.
5. Hua R, Wang Y. Skin Color Detection Based Super Pixel. In: 3rd IEEE International Conference on Computer and Communications (ICCC); 2017; Chengdu, China. doi: 10.1109/CompComm.2017.8322841.
6. Chakraborty BK, Bhuyan MK, Kumar S. Combining image and global pixel distribution model for skin colour segmentation. Pattern Recognition Letters 2017; 88: 33-40; doi: 10.1016/j.patrec.2017.01.005.
7. Shaik KB, Ganesan P, Kalist V, Sathish BS, Jenitha JMM. Comparative Study of Skin Color Detection and Segmentation in HSV and YCbCr Color Space. Procedia Computer Science 2015; 57: 41-48; doi: 10.1016/j.procs.2015.07.362.
8. Al-Mohair HK, Mohamad Saleh J, Suandi SA. Hybrid Human Skin Detection Using Neural Network and K-Means Clustering Technique. Applied Soft Computing 2015; 33: 337-347; doi: 10.1016/j.asoc.2015.04.046.

9. Tan WR, Chan CS, Yogarajah P, Condell J. A Fusion Approach for Efficient Human Skin Detection. IEEE Transactions on Industrial Informatics 2012; 8(1):138-147; doi: 10.1109/tii.2011.2172451.
10. Goyal M, Oakley A, Bansal P, Dancey D, Yap MH. Skin Lesion Segmentation in Dermoscopic Images With Ensemble Deep Learning Methods. IEEE Access 2020; 8: 4171-4181; doi: 10.1109/access.2019.2960504.
11. Hameed N, Shabut AM, Ghosh MK, Hossain MA. Multi-class multi-level classification algorithm for skin lesions classification using machine learning techniques. Expert Systems with Applications 2020; 141: 112961; doi: 10.1016/j.eswa.2019.112961.
12. Alkolifi Alenezi NS. A Method Of Skin Disease Detection Using Image Processing And Machine Learning. Procedia Computer Science 2019; 163: 85-92; doi: 10.1016/j.procs.2019.12.090.
13. Chatterjee S, Dey D, Munshi S. Integration of morphological preprocessing and fractal based feature extraction with recursive feature elimination for skin lesion types classification. Comput Methods Programs Biomed 2019; 178: 201-218; doi: 10.1016/j.cmpb.2019.06.018.
14. Wang X, Jiang X, Ding H, Liu J. Bi-directional Dermoscopic Feature Learning and Multi-scale Consistent Decision Fusion for Skin Lesion Segmentation. IEEE transactions on image processing 2019; 29: 3039-3051; doi: 10.1109/TIP.2019.2955297.
15. Pirnog I, Marcu I, Oprea C. Automated Segmentation of Pigmented Skin Lesions Images for Smartphone Applications. In: International Semiconductor Conference (CAS); 2019; Sinaia, Romania; doi: 10.1109/SMICND.2019.8923938.
16. Pathan S, Prabhu KG, Siddalingaswamy PC. Techniques and algorithms for computer aided diagnosis of pigmented skin lesions—A review. Biomedical Signal Processing and Control 2018; 39: 237-262; doi: 10.1016/j.bspc.2017.07.010.
17. Ahmad S. A usable real-time 3D hand tracker. In: Proceedings of 1994 28th Asilomar Conference on Signals, Systems and Computers; 1994; IEEE, 2: 1257-1261.
18. Hsu RL, Abdel-Mottaleb M, Jain AK. Face detection in color images. IEEE Transactions on Pattern Analysis and Machine Intelligence 2002; 24(5): 696-706; doi: 10.1109/34.1000242.
19. Mahmoodi MR and Sayedi SM. Leveraging spatial analysis on homogonous regions of color images for skin classification. In: 4th International Conference on Computer and Knowledge Engineering (ICCKE); 2014; Mashhad, Iran: IEEE, doi: 10.1109/ICCKE.2014.6993338.
20. skin image Data set with ground truth. [Online]. Available: https://www.researchgate.net/publication/257620282_skin_image_Data_set_with_ground_truth
21. Schmugge SJ, Jayaram S, Shin MC, Tsap LV. Objective evaluation of approaches of skin detection using ROC analysis. Computer vision and image understanding 2007; 108(1-2): 41-51.
22. Maxwell JC. On the Theory of Colours in Relation to Colour-blindness. 1855.
23. Maxwell JC. On the theory of three primary colours. 1861: Royal Institution of Great Britain.
24. Hunt RW. The specification of colour appearance. I. Concepts and terms. Color Research & Application 1977; 2(2):55-68.
25. Smith AR. Color gamut transform pairs. ACM Siggraph Computer Graphics 1978; 12(3): 12-19.
26. Wharton W, Howorth D. Principles of television reception. 1967: Pitman.
27. Rec. ITU-R BT.601-5. Studio Encoding Parameters of Digital Television for Standard 4:3 and Wide-screen 16:9 Aspect Ratios. (1982-1986-1990-1992-1994-1995): Section 3.5.
28. Vapnik V. Pattern recognition using generalized portrait method. Automation and remote control 1963; 24:774-780.
29. Aiserman M, Braverman EM, Rozonoer L. Theoretical foundations of the potential function method in pattern recognition. Avtomat. i Telemeh, 1964; 25(6): 917-936.
30. Boser BE, Guyon IM, Vapnik VN. A training algorithm for optimal margin classifiers. In: Proceedings of the fifth annual workshop on Computational learning theory; 1992: 144-152.