Multi-face detection based on downsampling and modified subtractive clustering for color images

This paper presents a multi-face detection method for color images. The method is based on the assumption that faces are well separated from the background by skin color detection. These faces can be located by the proposed method which modifies the subtractive clustering. The modified clustering algorithm proposes a new definition of distance for multi-face detection, and its key parameters can be predetermined adaptively by statistical information of face objects in the image. Downsampling is employed to reduce the computation of clustering and speed up the process of the proposed method. The effectiveness of the proposed method is illustrated by three experiments.

Color image segmentation using mean shift and improved ant clustering

To improve the segmentation quality and efficiency of color image,a novel approach which combines the advantages of the mean shift(MS) segmentation and improved ant clustering method is proposed.The regions which can preserve the discontinuity characteristics of an image are segmented by MS algorithm,and then they are represented by a graph in which every region is represented by a node.In order to solve the graph partition problem,an improved ant clustering algorithm,called similarity carrying ant model(SCAM-ant),is proposed,in which a new similarity calculation method is given.Using SCAM-ant,the maximum number of items that each ant can carry will increase,the clustering time will be effectively reduced,and globally optimized clustering can also be realized.Because the graph is not based on the pixels of original image but on the segmentation result of MS algorithm,the computational complexity is greatly reduced.Experiments show that the proposed method can realize color image segmentation efficiently,and compared with the conventional methods based on the image pixels,it improves the image segmentation quality and the anti-interference ability.

基于蝴蝶呈色规则的纺织品图案再生设计

蝶翼色彩娇艳华美、醒目多变,是纺织品图案仿生设计的重要灵感来源。为具象化表述不同类别蝴蝶的呈色特点,解析其色彩组合规则,以图谱方式描绘色彩构成,并应用到当代纺织品设计当中,选取5类不同呈色风格的蝴蝶图像,利用颜色聚类算法提取出颜色占比、颜色距离、节点共现率等关键指标,构建蝴蝶呈色关系图谱,以可视化的方式呈现不同类别蝴蝶的配色形式。实证分析与再生设计部分分别对5类典型蝴蝶,共计100幅样本图像颜色进行提取和分析,依据其呈色规则,复用至线稿纹样当中,形成近似蝴蝶呈色风格的纺织品图案,并在服装、家纺等产品中进行映射和虚拟展示。该方法能够对生物呈色进行量化,为时尚产品意象色彩的提取和应用提供了参考方案。

基于K-Means-NCS-ANOVA的八大民窑颜色聚类与应用偏好研究

中华陶瓷文化源远流长,颜色作为陶瓷的一种装饰,可以表达不同的设计理念、情感意识、地域特征和服务对象。为了更好地传承陶瓷艺术文化,本研究提出了一种基于K-means-NCS-ANOVA的颜色分类研究方法。首先,采用K-means颜色聚类、NCS颜色体系提取宋代八大民窑的颜色特征,分析八大瓷窑的区域特征及设计理念;基于上述分析结果制作问卷调查;并利用描述性分析、单因素方差分析(One-Way ANOVA),探究现代设计师对八大民窑颜色的应用偏好。由实验结果可知,设计师性别、专业、工龄也会对八大民窑颜色的应用偏好产生影响;景德镇窑的颜色最受现代设计师欢迎,而耀州窑、磁州窑、定窑的颜色已经不太符合现代审美。本研究采用现代人工智能技术识别八大民窑特征,调研现代设计师对八大民窑颜色的使用偏好,为文物识别、陶瓷文化传承及人才培养提供理论和技术支持。

基于聚类分析和判别分析的蛋壳颜色分级方法研究

为制定客观、准确的蛋壳颜色分级体系,研究在用Lab体系量化蛋壳颜色的基础上提出了一种蛋壳颜色分级标准的建立方法,先确定合适的聚类簇个数k,通过K-均值聚类分析处理训练样本,再通过贝叶斯判别分析检验聚类效果并获得各等级判别式,最后据此对测试样本进行分类,计算色差以检验分类效果。结果显示:训练样本的分类准确率达95.0%,测试样本各类别间颜色差异大,类别内颜色一致性较高,表明其分类效果良好。依据该方法可以针对特定群体构建专用分级标准,实现蛋壳颜色的合理分级与精准判定,进而为蛋壳颜色整齐度的提高提供指导。

基于聚类和Apriori算法的苗族女上装色彩分析

苗族服饰元素是中国服饰文化的重要组成部分,其色彩搭配方式蕴含着极大的文化价值,展现了中国传统设计理念。以苗族女上装图像作为研究对象,对其色彩进行提取与分析。通过K-means聚类得到10个整体色、5个主色及10个辅色代表色,在HSV色彩空间下分析苗族服饰色彩分布,最后采用Apriori算法挖掘配色规则并建立配色网络。结果显示,苗族女上装以中低饱和、中低明度的红、黄、蓝色系为主,图案与主体色彩呈现出强烈对比。将配色关系应用到设计实践中,可促进苗族服饰色彩的传承与保护,为研究民族传统服饰色彩提供一定的借鉴和参考。

基于模糊聚类的蓝莓成熟分级无损检测应用研究

由于现有的水果成熟分级技术通用性不够,不能对蓝莓成熟进行有效分级。因此提出基于模糊聚类的蓝莓成熟分级方法。通过图像处理技术分别对蓝莓的面积、周长、圆形度和着色分布进行计算,最后确定蓝莓成熟隶属函数和分级标准。试验表明,基于模糊聚类的蓝莓成熟分级方法能够有效地、快速地对蓝莓进行分级,其准确率为90%。

基于颜色和纹理特征聚类的彩色图像分割

针对传统彩色图像分割算法在轮廓模糊和纹理丰富区域分割效果差的缺点,本文提出基于颜色和纹理特征聚类的彩色图像分割算法。首先,采用基于图的图像分割算法多次分割图像,以得到多组超像素块;其次,提取超像素块的颜色特征和纹理特征,将其融合为一个特征向量,并使用k-means聚类对每组超像素块的特征向量聚类,以获得多组分割结果;最后,使用线性组合的方法融合多组分割结果,得到最终的分割图像。在公开数据集BSD500上与经典聚类算法SFFCM、AFCF相比较,实验结果表明本算法优于这些经典算法。

RAPD analysis on the four kinds of color-flowered Salvia splendens Ker-Gawl

In this study, we used RAPD to analyze four kinds of color-flowered Salvia splendens Ker-Gawl, and the optimal RAPD reaction conditions were the optimal reaction mixture （25 μL total volume） that contained 2.0 μL 10×buffer, 0.45 mmol·L^-1 dNTPs, 2.0 mmol· L^-1 Mg^2＋, 2 U Taq DNA polymerase, 0.30 umol·L^-2 primer and 40 ng genomic DNA. Total 84 bands were amplified from 12 primers used, and the differential bands had 28 bands, which was 33% of total bands. In cluster group analysis, the four kinds of color-flowered were divided into two styles. One style is that the red color and red-white color were grouped together, then they grouped with purple color into one cluster, and the white color was another style.

中国7个大区女性肤色测定和分级研究

为了探索中国女性肤色分布情况,利用同一型号的皮肤影像分析系统测量东北、华北、华东、华南、华中、西北和西南7个大区共10200名受试者的面部皮肤颜色。分析了这些样本在CIELAB色彩空间中的分布情况。并分析了多个色彩指标(L^(*)a^(*)b^(*)、ITA°、Hue、RGB、HSV)之间的相关性,最后选取了相关性较低的ITA°和Hue来绘制一个二维平面用于展示该7个大区样本的聚类结果。采用了潘通肤色指南对该7个大区的样本进行了归类。最后通过改进kmeans算法在肤色聚类中的应用将样本分为9类,并对样本进行了归类。结果表明,全国整体分布方面,本次采样中没有观察到皮肤颜色分级(skin color categories)的Ⅵ型的样本,大部分样本属于Ⅲ型和Ⅱ型;在剔除样本数少于100(总样本量的1%)的色号后,仅观察到潘通肤色指南12个色号,其中4Y07的样本最多;聚类划分中,聚类分类4观察到的样本最多,聚类分类8样本最少。区域分布方面,从ITA°和Hue的分布来看:东北肤色最浅最黄,西南大区肤色最红;潘通肤色指南显示,西南肤色色调最偏红(红调占比10.78%),华南皮肤色调最偏黄(红调占比5.73%);聚类划分显示,各大区聚类分类4的人数均是最多的;聚类分类8均是最少的。在各大区内部,各聚类分类占比最高的分别是东北(聚类分类0)、西南(聚类分类1)、华中(聚类分类2)、华北(聚类分类3)、华南(聚类分类4、6、7、8)和西北(聚类分类5)。

Modified Multispectral Space for Color Representation

Conventional multispectral space for color representation is modified by algorithm of cluster analysis and principal component analysis. Results show that the newer modified multispectral space not only keeping the structure of the original space but eliminating zero crosses as well its accuracy of color representation is higher than the conventional.

A Content-Based Parallel Image Retrieval System on Cluster Architectures

We propose a content-based parallel image retrieval system to achieve high responding ability. Our system is developed on cluster architectures. It has several retrieval. servers to supply the service of content-based image retrieval. It adopts the Browser/Server (B/S) mode. The users could visit our system though web pages. It uses the symmetrical color-spatial features (SCSF) to represent the content of an image. The SCSF is effective and efficient for image matching because it is independent of image distortion such as rotation and flip as well as it increases the matching accuracy. The SCSF was organized by M-tree, which could speedup the searching procedure. Our experiments show that the image matching is quickly and efficiently with the use of SCSF. And with the support of several retrieval servers, the system could respond to many users at mean time. Key words content-based image retrieval - cluster architecture - color-spatial feature - B/S mode - task parallel - WWW - Internet CLC number TP391 Foundation item: Supported by the National Natural Science Foundation of China (60173058)Biography: ZHOU Bing (1975-), male, Ph. D candidate, reseach direction: data mining, content-based image retrieval.

Improved color feature arrangement for mean shift tracking

In order to reduce redundant empty bin capacity in the probability representation,we present a new color feature arrangement mechanism for mean shift tracking objects.In the proposed mechanism,the important optimal color,or we call it optimal color vector,is clustered by closing Euclidean distance which happens inside the original RGB color 3-D spatial domain.After obtaining clustering colors from the reference image RGB spatial domain,novel clustering groups substitute for original color data.So the new color substitution distribution is as similar as the original one.And then target region in the candidate frame is mapped by the constructed optimal clustering colors and the cluster Indices.In the final,mean shift algorithm gives a performance in the new optimal color distribution.Comparison under the same circumstance between the proposed algorithm and conventional mean shift algorithm shows that the former has a certain advantage in computation cost.

Application of nonlinear color matching model to four-color ink-jet printing

Through discussing the color matching technology and its application in printing industry the conventional approaches commonly used in color matching, and the difficulties in color matching, a nonlinear color matching model based on two step learning is established by finding a linear model by learning pure color data first and then a nonlinear modification model by learning mixed color data. Nonlinear multiple regression is used to fit the parameters of the modification model. Nonlinear modification function is discovered by BACON system by learning mixture data. Experiment results indicate that nonlinear color conversion by two step learning can further improve the accuracy when it is used for straightforward conversion from RGB to CMYK. An improved separation model based on GCR concept is proposed to solve the problem of gray balance and it can be used for three to four color conversion as well. The method proposed has better learning ability and faster printing speed than other historical approaches when it is applied to four color ink jet printing.

基于PCA颜色特征聚类的彩色图像分割

针对RGB颜色特征各颜色分量高度相关问题,本文提出基于PCA颜色特征聚类的彩色图像分割算法。首先,采用超像素算法对图像进行预分割,将基于像素的聚类转化为基于超像素的聚类;其次,提取超像素PCA颜色特征和坐标特征;最后,对超像素进行k最近邻密度峰值聚类,完成图像分割。在BSDS500和MSRC数据集上的实验结果表明,本文所提算法能较好地实现彩色图像的分割,在视觉效果和性能指标上均得到较好的结果。

A study of variable stars in the open cluster NGC 1582 and its surrounding field

This paper presents Charge-Coupled Device time-series photometric observations of the open cluster NGC 1582 and its surrounding field with Johnson B, V and R filters by using the Nanshan 1 m telescope administered by Xinjiang Astronomical Observatory. 19 variable stars and three variable candi- dates were detected in a 45＇ - 48.75＇ field around the cluster. 12 of the variable stars are newly-discovered variable objects. The physical properties, classifications and memberships of these 22 objects are studied through their light curves, their positions on the color-magnitude diagram and with archival data from the Naval Observatory Merged Astrometric Dataset. Among these objects, five are eclipsing binary systems, six are pulsating variable stars including one known 6 Scuti star and one newly-discovered RR Lyrae star. The distance to the RR Lyrae star is estimated to be 7.9 - 0.3 kpc, indicating that the star is located far behind the cluster. Four variable stars are probable members of the cluster, and 13 of the 22 objects are confirmed to be field stars.

A Clustering Algorithm for Key Frame Extraction Based on Density Peak

Aiming at the problem of video key frame extraction, a density peak clustering algorithm is proposed, which uses the HSV histogram to transform high-dimensional abstract video image data into quantifiable low-dimensional data, and reduces the computational complexity while capturing image features. On this basis, the density peak clustering algorithm is used to cluster these low-dimensional data and find the cluster centers. Combining the clustering results, the final key frames are obtained. A large number of key frame extraction experiments for different types of videos show that the algorithm can extract different number of key frames by combining video content, overcome the shortcoming of traditional key frame extraction algorithm which can only extract a fixed number of key frames, and the extracted key frames can represent the main content of video accurately.

基于珍珠数字图像的颜色特征提取及检测方法研究

为了优化珍珠颜色特征提取,提高珍珠颜色检测准确率,提出结合K-means聚类和局部梯度的阴影检测算法,结果表明该算法可以精确检测珍珠数字图像中珍珠的阴影,消除了阴影对提取颜色特征的干扰。在Lab颜色空间,提出基于珍珠回音廊效应区域的颜色特征提取,使用GA-SVM作为珍珠颜色识别方法,提出使用二次颜色检测策略,通过两次颜色检测确定珍珠颜色类别。通过对比实验结果表明,珍珠体色色系检测准确率达到100%,珍珠颜色检测准确率达到98.7878%。