Real-time hand area segmentation for hand gesture recognition in desktop environment

Abstract

the process of separating the hand area from a complex background, knownas hand segmentation, is a prerequisite for any vision-based hand gesture recognitionsystem. In some applications, only a rough estimate of the hand area is needed, but in otherapplications an exact segmentation of the hand, if possible, is needed. In this paper, threemethods for extracting the hand from the background in real-time were tested. Thesemethods use off-line learning of skin color; these methods are Histogram Intersection,Color Histogram, and Skin Color Modeling and Adaptation. The three methods weretested using a video sequence of 100 frames using four different lighting conditions, with400 frames in total. The different lighting conditions are fluorescent light only, a mixture offluorescent and daylight, daylight without the sun light, and daylight with the sun light.These video streams were taken from the same person under the above different lightingconditions. A comparative study between the three methods was performed. The resultsshowed that hand segmentation using Skin Color Modeling and Adaptation withFluorescent light produced the best results among the three methods. The objective of ourresearch is to accurately recognize the hand gestures, and then use it in many differentapplications. The work in this paper is the first stage in our research. The contribution inthis paper is the comparative study between three different techniques that use skin-colormodeling under different lighting conditions.