Skin detection is used in many applications, such as face recognition, handtracking, and human-computer interaction. There are many skin color detectionalgorithms that are used to extract human skin color regions that are based on thethresholding technique since it is simple and fast for computation. The efficiency ofeach color space depends on its robustness to the change in lighting and the ability todistinguish skin color pixels in images that have a complex background. For moreaccurate skin detection, we are proposing a new threshold based on RGB and YUVcolor spaces. The proposed approach starts by converting the RGB color space to theYUV color model. Then it separates the Y channel, which represents the intensity of thecolor model from the U and V channels to eliminate the effects of luminance. After thatthe threshold values are selected based on the testing of the boundary of skin colorswith the help of the color histogram. Finally, the threshold was applied to the inputimage to extract skin parts. The detected skin regions were quantitatively compared tothe actual skin parts in the input images to measure the accuracy and to compare theresults of our threshold to the results of other's thresholds to prove the efficiency of ourapproach. The results of the experiment show that the proposed threshold is morerobust in terms of dealing with the complex background and light conditions than others.