Adaptive Skin Detection


In principle, the proposed approach follows a two-step process (Figure 1). For a given image, we first perform a rough skin classification using a generic skin-model which defines the Skin-Similar space. The Skin-Similar space often contains many non-skin pixels due to the inevitable overlap in the color space between skin pixels and some non-skin pixels under the generic skin-model. The objective of the second step is to reduce the false-positive rate by analyzing the image under consideration.  Specifically, in the second step, a Gaussian Mixture Model (GMM), specific to the image under consideration and refined from its Skin-Similar space, is derived using the standard Expectation-Maximization (EM) algorithm. We then use a Support Vector Machine (SVM) classifier to identify the skin Gaussian from the trained GMM by incorporating spatial and shape information of the skin pixels.



mask 1 mask 2 mask 3 mask 4 mask 5mask 6

Image samples by a generic skin-model (left) vs. our adaptive skin-model (right)


• Qiang Zhu, Ching-Tung Wu, Kwang-Ting Cheng, Yi-Leh Wu. An Adaptive Skin Model and Its Application to Objectionable Image Filtering (Full Paper), ACM International Conference on Multimedia 2004 (ACM MM 2004), October 10-16, New York, USA.
• Qiang Zhu, Kwang-Ting Cheng, Ching-Tung Wu, Yi-Leh Wu. Adaptive Learning of an Accurate Skin-Color Model (Oral session), IEEE 6th International Conference on Automatic Face and Gesture Recognition (FG 2004), May 17-19, Seoul, Korea.
• Qiang Zhu, Kwang-Ting Cheng, Ching-Tung Wu. A Unified Adaptive Approach to Accurate Skin Detection (Oral session), IEEE International Conference on Image Processing 2004 (ICIP 2004), October 24-27,


Our test database for skin detection including 555 images with labeled ground truth (download)

<back to research>