A COMPARATIVE STUDY OF CLASSIFICATION METHODS ON HUMAN SKIN DETECTION FROM RGB AND YCBCR REPRESENTED COLOR IMAGES

Year 2020, Volume: 21 , 40 - 44, 27.11.2020

Utku Kaya , Murat Başaran

https://doi.org/10.18038/estubtda.818452

Abstract

Skin detection has an important place in image processing. Human-computer interaction has made this study area very popular. The most common color space used in skin detection is Red Green and Blue but RGB space can be converted into YCbCr space. Both features give strong information about the properties of the images. In this study, RGB and YCbCr spaces are used to detect human skin. The extracted features are trained by several classification methods. The obtained features are used to segment the human skin by using the chosen classification algorithm and finally, the promising performance results are presented comparatively with the most commonly used classifications methods in the literature.

Keywords

Feature extraction, Image segmentation, YCbCr

References

• [1] Sumithra R, Mahamad Suhil and D S. Guru. Segmentation and Classification of Skin Lesions for Disease Diagnosis. Procedia Computer Science 45 (2015): 76-85.
• [2] Lee Jiann-Shu, et al. Naked Image Detection Based on Adaptive and Extensible Skin Color Model. Pattern Recognition 40.8 (2007): 2261-2270.
• [3] Basilio Jorge Alberto Marcial, et al. Explicit Image Detection using YCbCr Space Color Model as Skin Detection Applications of Mathematics and Computer Engineering (2011): 123-128.
• [4] Shaik Khamar Basha, et al. Comparative Study of Skin Color Detection and Segmentation in HSV and YCbCr Color Space. Procedia Computer Science 57.12 (2015): 41-48.
• [5] Schmugge SJ, et al. Objective Evaluation of Approaches of Skin Detection using ROC Analysis. Computer Vision and Image Understanding 108.1-2 (2007): 41-51.
• [6] Dal Pozzolo Andrea et al. Calibrating Probability with Undersampling for Unbalanced Classification. 2015 IEEE Symposium Series on Computational Intelligence. IEEE, 2015.
• [7] Dal Pozzolo, Andrea, Olivier Caelen, and Gianluca Bontempi. When is undersampling effective in unbalanced classification tasks? Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Springer, Cham, 2015.
• [8] Grandvalet, Yves, Johnny Mariéthoz, and Samy Bengio. A Probabilistic Interpretation of SVMs with An Application to Unbalanced Classification. Advances in Neural Information Processing Systems. 2006.