基于唇色信息的唇部检测方法研究

唇部检测是唇读识别的基本步骤,在研究人类视觉和唇色聚类的基础上,分析了唇色和肤色的聚类性,提出了利用神经网络单层感知器学习算法对彩色人脸图像的唇部进行定位的新方法。实验表明,采用感知器学习算法比F isher方法的唇部定位更准确,轮廓更清晰,更有利于唇部口型的识别。     

基于几何特征和支持向量机的人脸检测

针对人脸检测中的非线性和降维问题提出了一种有效的人脸检测方法。首先基于人脸的肤色和几何特征．通过局部自适应门限方法提取图象边缘，用几何规则和颜色特征筛选出候选眼睛块。然后采用改进的四边界sobel算子对眼睛精确定位。最后使用训练好的支撑向量机来验证。该方法可以实现多尺度多角度的彩色图像中的正面人脸检测，实验结果令人满意。     

基于惩罚感知器的唇部定位方法

唇部检测是唇读识别的基本步骤,在研究人类视觉和唇色聚类的基础上,分析了唇色和肤色的聚类性,提出了基于惩罚感知器学习算法对彩色人脸图像的唇部进行定位的新方法.实验表明,采用感知器学习算法只需对所有输入图像进行一次训练样本的采集,就可以得到了正确的权阈值,准确对所有不同人脸的唇部图片进行定位,相比于Fisher变换每次都需对输入图像进行样本采集,感知器学习算法唇部定位更准确,轮廓更清晰,且更具有通用性,有利于唇部口型的识别.     

A flower image retrieval method based on ROI feature

Flower image retrieval is a very important step for computer-aided plant species recognition.In this paper,we propose an efficient segmentation method based on color clustering and domain knowledge to extract flower regions from flower images.For flower retrieval,we use the color histogram of a flower region to characterize the color features of flower and two shape-based features sets,Centroid-Contour Distance(CCD)and Angle Code Histogram(ACH),to characterize the shape features of a flower contour.Experimental results showed that our flower region extraction method based on color clustering and domain knowledge can produce accurate flower regions.Flower retrieval results on a database of 885 flower images collected from 14 plant species showed that our Region-of-Interest(ROD based retrieval approach using both color and shape features can perform better than a method based on the global color histogram proposed by Swain and Ballard(1991)and a method based on domain knowledge-driven segmentation and color names proposed by Das et al.(1999).     

A flower image retrieval method based on ROI feature

INTRODUCTION There are about 250000 named species offlowering plants and many plant species that havenot been classified and named. Plant classificationand identification is a very old field. So far, thistime-consuming process has mainly been carriedout by taxonomists and/or botanists. A significantimprovement can be expected if the plant identifi-cation can be carried out by a computer automati-cally or semi-automatically with the aid of imageprocessing and computer vision techniqu…     

基于自适应聚类和色差分析的烟草异物在线识别算法研究

提出一种利用聚类和色差分析的烟草异物在线识别算法,采用自适应ISODATA聚类取单元颜色特征,并分析烟叶和异物各分量的分布差异,将单元特征各分量根据直方图分布量化到HIS颜色空间中,从而得到样本学习结果并进行识别。实验结果表明,该算法的平均识别率达到95%,误识率在5%以下。     

FCM改进方法在图像分割中的知识发现

考虑到图像存在异常像素,将邻域因素考虑在内对模糊C-均值聚类算法(FCM)和异常像素检测算法(APD)提出了改进。首先,提出了邻域因素的邻域-FCM(N-FCM),然后,提出了模糊异常像素检测算法(Fuzzy-APD)。实验过程中,选择噪声图像、彩色图像作为实验图像,对FCM和N-FCM算法进行性能比较,证实相比于FCM算法,N-FCM算法的收敛性明显提高,图像分割的正确率进一步改善;同时从图像中获取部分像素进行异常像素检测,实验证实相比于异常像素检测,Fuzzy-APD准确性更高。     

Local and global approaches of affinity propagation clustering for large scale data

Recently a new clustering algorithm called ＇affinity propagation＇ （AP） has been proposed, which efficiently clustered sparsely related data by passing messages between data points. However, we want to cluster large scale data where the similarities are not sparse in many cases. This paper presents two variants of AP for grouping large scale data with a dense similarity matrix. The local approach is partition affinity propagation （PAP） and the global method is landmark affinity propagation （LAP）. PAP passes messages in the subsets of data first and then merges them as the number of initial step of iterations; it can effectively reduce the number of iterations of clustering. LAP passes messages between the landmark data points first and then clusters non-landmark data points; it is a large global approximation method to speed up clustering. Experiments are conducted on many datasets, such as random data points, manifold subspaces, images of faces and Chinese calligraphy, and the results demonstrate that the two approaches are feasible and practicable.     

融合高斯混合模型和prewitt算子的运动目标检测

提出一种融合高斯混合模型和prewitt算子的运动目标检测算法.通过高斯混合模型拟合背景信息,利用prewitt算子提取图像的边缘特征信息,将两者融合起来.边缘信息反映了局部区域内容的结构信息,可作为颜色信息的补偿;模型保证了在线更新背景信息时的稳定性和收敛性,同时弥补了目标分割中颜色信息接近时容易导致误判的不足.实验结果表明,与一般高斯混合模型比较,本方法具有较高的分割精度,提高了目标检测的鲁棒性.     

融合音频特征的比赛场地主颜色聚类算法

针对当前手动分割视频获取主颜色实验帧序列,导致算法鲁棒性差,自动化程度低等问题,着重分析了体育比赛的音频特征及场地颜色特征,提出一种融合音频特征的主颜色聚类算法。实验结果表明,该算法不需人工预处理,针对不同比赛场地具有良好的鲁棒性,通过音频特征的辅助分析,有效提高主颜色提取准确率,同时降低时间复杂度。     

跳水运动视频中的运动目标分割

针对跳水运动视频中的人体运动目标分割问题,提出一种简单有效的基于颜色特征运动目标检测及分割算法。首帧进行图像预处理,利用色相和亮度两个分量加强颜色差异,然后使用OTSU算法对图像进行阈值分割。结合RGB颜色空间启发式肤色聚类结果确定运动目标所在的连通区域,最终完成首帧运动目标的自动检测。有效地克服了复杂背景变化的影响,能够快速实现跳水运动目标的分割,且对运动对象的快速整体运动有较强的鲁棒性。     

基于K-means彩色图像分割的六价铬检测方法

依据重金属残留现场快速检测的要求,利用二苯碳酰二肼分光光度法显色原理制成六价铬检测试纸,对溶液中的六价铬离子发生紫红色的显色反应,设计一种K-means聚类算法对该显色反应图像进行分析,获得聚类分割的彩色目标区域。基于RGB彩色空间模型提取试纸中的R、G、B 3个颜色分量特征值,通过分析彩色图像预处理与切割、拟合R、G、B与浓度之间的关系等阶段,实现基于机器视觉的六价铬检测系统的研究。     

一种改进的聚类和孤立点检测算法

对基于距离的聚类及基于密度的孤立点检测方法进行了分析研究,提出了一种基于距离和密度的聚类和孤立点检测算法DDBCOD.该算法根据距离和密度阈值对数据进行聚类,并发现数据中的孤立点.实验表明,该算法能够识别任意形状的聚类,对高维数据有效,能够很好的识别出孤立点.     

A new algorithm based on metaheuristics for data clustering

This paper presents a new algorithm for clustering a large amount of data.We improved the ant colony clustering algorithm that uses an ant’s swarm intelligence,and tried to overcome the weakness of the classical cluster analysis methods.In our proposed algorithm,improvements in the efficiency of an agent operation were achieved,and a new function "cluster condensation" was added.Our proposed algorithm is a processing method by which a cluster size is reduced by uniting similar objects and incorporating them into the cluster condensation.Compared with classical cluster analysis methods,the number of steps required to complete the clustering can be suppressed to 1% or less by performing this procedure,and the dispersion of the result can also be reduced.Moreover,our clustering algorithm has the advantage of being possible even in a small-field cluster condensation.In addition,the number of objects that exist in the field decreases because the cluster condenses;therefore,it becomes possible to add an object to a space that has become empty.In other words,first,the majority of data is put on standby.They are then clustered,gradually adding parts of the standby data to the clustering data.The method can be adopted for a large amount of data.Numerical experiments confirmed that our proposed algorithm can theoretically applied to an unrestricted volume of data.     

基于机器视觉的汽车角窗玻璃混线检测算法

针对汽车玻璃角窗生产线上轮廓、材质与厚度相近似的汽车玻璃容易产生混淆的问题,提出融合轮廓特征与颜色特征的汽车玻璃混线检测算法。通过改进的几何矩匹配算法实现汽车玻璃的轮廓检测;利用色彩特征实现汽车玻璃的材质与厚度的检测,结合轮廓特征与色彩特征实现了汽车玻璃的混线检测。实验证明,提出的混线检测算法有效提高了汽车玻璃混线检测的准确率,有利于提升汽车玻璃检测的自动化水平。     

复杂背景下一种新的肤色检测方法

通过对复杂背景下的人脸图片进行自适应光照补偿,建立高斯肤色模型,并利用改进的Otsu算法进行人脸肤色检测.实验证明,该方法效率高,对背景、尺寸、旋转角度等细节具有很好的适应性,在人脸实时检测中具有很好的应用价值.     

基于聚类分析的非监督式异常检测研究

传统的异常检测方法要求训练数据集完全由已标记为正常的实例所构成，但在实际应用中，很难得到这样的训练数据集。本文提出了一种基于聚类分析的非监督式异常检测方法，该方法的优点在于不需要任何标记数据，并且能够实现网络连接数据的实时检测。实验采用KDD99数据集进行测试，结果表明，该方法具有比较高的检测性能。     

一种启发式聚类特征选择方法

为了使聚类可以在低维数据空间中进行,提出了一种新的聚类特征选择方法.该方法分3个步骤,每个步骤都在一个wrapper框架中执行.首先,将所有原始特征都按照重要性进行排序,引入一个特征重要性评价函数E(f);然后,顺序地选择特征组成重要特征子集;最后,去除重要特征子集中可能存在的冗余特征.由于是顺序选择特征而不是在巨大的特征子集空间中进行搜索,因此算法效率很高.实验结果表明该方法可以找出有助于聚类的重要特征子集,并且可以去掉那些不利于聚类的特征.     

A color based face detection system using multiple templates

A color based system using multiple templates was developed and implemented for detecting human faces in color images. The algorithm consists of three image processing steps. The first step is human skin color statistics. Then it separates skin regions from non-skin regions. After that, it locates the frontal human face(s) within the skin regions. In the first step, 250 skin samples from persons of different ethnicities are used to determine the color distribution of human skin in chromatic color space in order to get a chroma chart showing likelihoods of skin colors. This chroma chart is used to generate, from the original color image, a gray scale image whose gray value at a pixel shows its likelihood of representing the skin. The algorithm uses an adaptive thresholding process to achieve the optimal threshold value for dividing the gray scale image into separate skin regions from non skin regions. Finally, multiple face templates matching is used to determine if a given skin region represents a frontal human face or not. Test of the system with more than 400 color images showed that the resulting detection rate was 83%, which is better than most color-based face detection systems. The average speed for face detection is 0.8 second/image (400×300 pixels) on a Pentium 3 (800 MHz) PC. Project (No. 60203013) supported by National Natural Science Foundation of China