An objectifying system for color inspections of traditional Chinese medicine （CITCM） is developed. The entire system includes two parts ： The hardware and the software. The hardware is an image acquiring device under a standard lighting condition, and it mainly includes a xenon lamp with color temperature of 5 500 K as light source, an integrating sphere used for diffusing light and a high resolution CCD camera. The software is used for digital image processing, and the procedure is divided into three steps. Firstly the skin/non-skin classifi- cation is performed by utilizing the threshold in chrominance channels of the RGB color space. Secondly, the fa- cial features are localized by using the image segmentation and coordinates sorting. Finally, the facial special re- gion（SR） corresponding to five internal organs is achieved by utilizing masks designed to take advantage of mor- phology. Subsequently, the chromaticity is calculated. The system is tested by taking 83 samples of 30 young and 53 elderly people. The experiment shows that there is significant difference of all SRs between the young and the elderly, and the system has better performance for objectifying research of CITCM.
支持向量机(Support vector machine,SVM)作为一种经典的分类方法,已经广泛应用于各种领域中。然而,标准支持向量机在分类决策中面临以下问题:(1)未考虑分类数据的分布特征;(2)忽略了样本类别间的相对关系;(3)无法解决大规模分类问题。鉴于此,提出融合数据分布特征的保序学习机(Rank preservation learning machine based on data distribution fusion,RPLM-DDF)。该方法通过引入类内离散度表征数据的分布特征;通过各类样本数据中心位置相对不变保证全局样本顺序不变;通过建立所提方法和核心向量机对偶形式的等价性解决了大规模分类问题。在人工数据集、中小规模数据集和大规模数据集上的比较实验验证所提方法的有效性。
