A comparative assessment of three approaches to pixel-level human skin-detection
A comparative assessment of three approaches to pixel-level human skin-detection
复制标题
三种像素级人体皮肤检测方法的比较评估
DOI：
10.1109/icpr.2000.905653
复制
发表时间：
2000
期刊：
影响因子：
--
通讯作者：
J. Mason
中科院分区：
文献类型：
--
作者：
J. Brand;J. Mason
本文评估了三种不同的像素级人体皮肤检测方法的优点。这三种方法的基础已在文献中报道。前两种方法分别使用简单的比例和色彩空间变换，而第三种方法是基于3D RGB概率图的数值有效方法，由Rehg-Jones（1999）首次实现。贝叶斯概率只有在有适当标记的大型数据库可用的情况下才有可能计算。来自康柏皮肤和非皮肤数据库的12000多张图像被用于定量评估这三种方法。根据经验确定阈值以检测95%的所有皮肤相关像素，然后根据不正确接受的非皮肤像素的百分比进行评估。根据3D概率图，这些错误接受率中最低的约为20%。
This paper assesses the merits of three different approaches to pixel-level human skin detection. The basis for the 3 approaches has been reported in the literature. The first two approaches use simple ratios and colour space transforms respectively, whereas the third is a numerically efficient approach based on a 3D RGB probability map, first implemented by Rehg-Jones (1999). The Bayesian probabilities are made possible to compute only with the availability of a large appropriately labeled database. Over 12000 images from the Compaq skin and non-skin databases are used to quantitatively assess the three approaches. Thresholds are determined empirically to detect 95% of all skin-associated pixels and assessment is then made in terms of the percentage of non-skin pixels incorrectly accepted. The lowest of these false acceptance rates is found to be about 20% given by the 3D probability map.