传统服饰云肩实物图像主色的智能检测

为解决获取传统服饰实物图像色彩耗时且缺乏准确性问题，以传统服饰的云肩为例，借助均值漂移（Mean-shift）聚类法，提出了一种检测传统服饰实物图像颜色的方法。运用单反数码相机进行实物图像采集；对所得初始图像的R、G、B3个颜色通道进行去噪处理；再将图像RGB颜色空间的特征向量转换至CIE L*a*b*颜色空间中，利用大津法阈值原理（自适应阈值算法）分割被测图像中云肩实物与背景；最后采用Mean-shift聚类算法，将被测图像的颜色像素分割为若干有效的集群，同时从这些集群中提取云肩主要色彩。实验结果表明，该算法可较为准确地从云肩图像中提取主色，且当Mean-shift聚类算法的带宽被设定为0.05时，分类颜色结果更为准确。

Intelligent inspection of dominant colors for Chinese traditional folk Yunjian

In order to solve the problems of time-consuming and poor accuracy during the process of achievement colors from the images of tarditional costumes, an effective color clustering method was developed for Chinese traditional costumes Yunjian image Mean-shift clustering algorithm.A digitalSingle Lens Reflex camera is used to capture the costumes images.The sub-images in the three color channels are filtered by median filter separately. Thirdly, the filtered images are segmented based on the background color in the Lab color space, and the object costumes is separated from the background. Fourthly, the pixels of the costume image are classified into several clusters by Mean shift clustering algorithm, and the dominate colors are extracted from the classification results. The experimental results demonstrate that the proposed method can extract the dominant colors from costumes images with great accuracy when the bandwidth of Mean shift clustering algorithm is set as 0.05.