作者: Jose M. Chaves-González , Miguel A. Vega-Rodríguez , Juan A. Gómez-Pulido , Juan M. Sánchez-Pérez
DOI: 10.1016/J.DSP.2009.10.008
关键词:
摘要: Skin colour detection is a technique very used in most of face detectors to find faces images or videos. However, there not common opinion about which space the best choice do this task. Therefore, motivation for our study discover model option build an efficient detector can be embedded functional recognition system. We have studied 10 and spaces doing different comparisons among them, order know one human skin detection. In concrete, we models: RGB, CMY, YUV, YIQ, YPbPr, YCbCr, YCgCr, YDbDr, HSV-or HSI-and CIE-XYZ. To make comparison 15 truth where clearly separated from rest image (background, eyes, lips, hair, etc.). Thus compare at level pixel each model, detailed format. present final conclusions comparing results, such as: right detections, false positives negatives space. According obtained appropriate are HSV (the winner study), models YCgCr YDbDr.