Face detection and recognition are affected greatly by unequal luminance, color excursion and background interference. For improving skin detection rates of color face images in the presence of unequal luminance, color excursion and background interference, this paper proposes an approach for automatic skin detection. This approach globally corrects the color excursion using the X, Y, Z color components. Then it establishes a self-adaptive nonlinear amendment function using the a', b'and L' components, and locally corrects the R, G, B color components of row-column transformed sub-block images to balance the global luminance and color. Finally, it constructs an L'a'b'three-dimensional semi-supervised dual-probability skin model, based on which automatic skin detection can be realized. The experimental results demonstrated that this approach has great adaptability, a high detection rate and speed.