Luminance adapted skin color modeling for the robust detection of skin areas

Abstract

Statistical models of color channels have been used for the detection of skin areas. However, since the distribution of colors also change as the luminance varies, color distribution models without considering the luminance variation do not work well for the images taken under various illumination conditions. Hence we propose a new skin detection algorithm that considers the luminance value in modeling the color distribution. For implementing this idea, we need a sample of skin color in the image, which can be obtained from the face. It is noted that the faces can be detected without color feature, but by using only structural features such as eyes, mouth, etc. In our algorithm, the eye detector and elliptical boundary are used to detect the face. From the face region, joint Gaussian distributions of color components with respect to the luminance values are obtained. Then, each pixel in the image is classified into skin or non-skin using the statistics obtained from the face region. Experimental results show that the proposed skin color model outperforms the conventional methods in terms of the detection accuracy and F-score.

A New Convolutional Network-in-Network Structure and Its Applications in Skin Detection, Semantic Segmentation, and Artifact Reduction

“…We compare the proposed method using benchmark skin dataset with other methods: Bayesian [16], FPSD [18], DSPF [19], FSD [41], and LASD [14]. FPSD and DSPF are based on seed propagation over the graph representation of images.…”

“…Accuracy Precision Recall F-measure Bayesian [16] 0.8237 0.6881 0.8972 0.7788 FSD [41] 0.8255 0.8077 0.6851 0.7414 LASD [14] 0.8361 0.7954 0.8275 0.8111 FPSD [18] 0.8419 0.7837 0.8991 0.8070 DSPF [19] 0 Comparison on Pratheepan dataset is shown in Figure 8, where it can be seen that the proposed method has the best performance on both PR and ROC curves. Moreover, it has much better performance than others even in the case of using only gray channel image.…”

Improved Dynamic Threshold Method for Skin Colour Detection Using Multi-Colour Space

“…For the past few years, researchers have shifted to dynamic or adaptive approach which is based on the face or hand adaptation as detailed in Table 1 (Bianco et al, 2013;Hsieh et al, 2012;Hwang et al, 2013;Ibrahim et al, 2012;Tan et al, 2012;Taylor and Morris, 2014;Yogarajah et al, 2012). This approach requires no offline training of skin samples and it is less complex.…”