Unsupervised Color Segmentation with Reconstructed Spatial Weighted Gaussian Mixture Model and Random Color Histogram

Image classification and unsupervised image segmentation can be achieved using the Gaussian mixture model.Although the Gaussian mixture model enhances the flexibility of image segmentation,it does not reflect spatial information and is sensitive to the segmentation parameter.In this study,we first present an efficient algorithm that incorporates spatial information into the Gaussian mixture model(GMM)without parameter estimation.The proposed model highlights the residual region with considerable information and constructs color saliency.Second,we incorporate the content-based color saliency as spatial information in the Gaussian mixture model.The segmentation is performed by clustering each pixel into an appropriate component according to the expectation maximization and maximum criteria.Finally,the random color histogram assigns a unique color to each cluster and creates an attractive color by default for segmentation.A random color histogram serves as an effective tool for data visualization and is instrumental in the creation of generative art,facilitating both analytical and aesthetic objectives.For experiments,we have used the Berkeley segmentation dataset BSDS-500 and Microsoft Research in Cambridge dataset.In the study,the proposed model showcases notable advancements in unsupervised image segmentation,with probabilistic rand index(PRI)values reaching 0.80,BDE scores as low as 12.25 and 12.02,compactness variations at 0.59 and 0.7,and variation of information(VI)reduced to 2.0 and 1.49 for the BSDS-500 and MSRC datasets,respectively,outperforming current leading-edge methods and yielding more precise segmentations.

An improved mean shift tracking algorithm based on double weighted color histogram

In practical application,mean shift tracking algorithm is easy to generate tracking drift when the target and the background have similar color distribution.Based on the mean shift algorithm,a kind of background weaken weight is proposed in the paper firstly.Combining with the object center weight based on the kernel function,the problem of interference of the similar color background can be solved.And then,a model updating strategy is presented to improve the tracking robustness on the influence of occlusion,illumination,deformation and so on.With the test on the sequence of Tiger,the proposed approach provides better performance than the original mean shift tracking algorithm.

Content-based Image Retrieval Using Color Histogram

This paper introduces the principles of using color histogram to match images in CBIR. And a prototype CBIR system is designed with color matching function. A new method using 2-dimensional color histogram based on hue and saturation to extract and represent color information of an image is presented. We also improve the Euclidean-distance algorithm by adding Center of Color to it. The experiment shows modifications made to Euclidean-distance signif-icantly elevate the quality and efficiency of retrieval.

An Improved Color Cast Detection Method Based on an AB-Chromaticity Histogram

AB-chromaticity histogram analysis works well most of the time, but it may not work well when the color cast is not severe. To overcome this problem, we propose an improved, two-step automatic cast-detection method. First, we compute the RGB color variance to evaluate the quality of the input image. If this variance is very small, we extract near-neutral color areas and compute the local ab-chromaticity histogram. We use this local ab-chromaticity histogram to evaluate the quality of the input image. This method has been tested in ZTE＇ s video surveil- lance system. The results show that the proposed method pro- duces better results based on subjective evaluation and is more efficient in various conditions.

基于Raspberry Pi的安全帽识别系统设计与实现

为了便于施工危险区域人员的自动化识别,提出了一种基于Raspberry Pi的安全帽识别算法。该算法将摄像头采集到的原始视频图像进行滤波、形态学等处理,再对图像中的安全帽进行识别。对于彩色安全帽,将原始图像转换到HSV空间,根据不同颜色色调阈值的设定同时识别红、黄、蓝三种颜色的安全帽,并结合形状特征剔除错误目标。对于白色安全帽,将原始图像转化成B通道下的灰度图像,解决了将黄色误检为白色的问题。采用V通道直方图均衡化的方法,提升了昏暗光线条件下的图像亮度。实验结果表明:在无需提前训练的情况下,算法对于单色安全帽识别准确率超过了91%,对于多色安全帽识别率超过了90%,为施工危险区域的安全隐患排查和作业管控提供了解决方案。

基于颜色直方图的电路板表面缺陷检测

为了提高废旧电路板的回收再利用率,针对回收电路板常见表面缺陷,在均匀分块基础上,提出了四叉树分裂颜色直方图缺陷检测方法。该方法能快速定位电路板表面缺陷,并通过支持向量机(SVM)实现缺陷分类,进而为电路板的二次利用提供质量保障。重点分析了分块大小与判断阈值对缺陷定位结果的影响,在保证检测精度的同时,检测速度相比均匀分块方法得到明显提升。与Faster-RCNN网络方法进行对比,结果表明该方法定位效果好,分类准确率平均达81%。

大视场高分辨率无色差的复眼相机阵列系统

为了解决单相机平台受高分辨率与大视场角之间矛盾制约的问题,本文提出了一种大视场、高分辨率、无色差的复眼相机阵列系统。结合人眼视觉成像理论,建立非均匀采样的仿生视觉模型,降低系统输入端的数据冗余;设计了一种多图像平滑加权融合算法,实现大视场图像无缝拼接;提出了一种基于多级迭代直方图匹配的色彩校正算法,提高了不同子相机间的色彩一致性;利用相邻子相机间重叠区域,对感兴趣区域(Region of Interest,ROI)进行多图像超分辨率重建。最终搭建了曲面相机阵列系统,实现了无色差大视场高分辨率图像的获取。实验结果表明,该系统能够达到单个子相机9倍的视场角与分辨率,并实现了ROI的4倍超分辨率重建。相比于典型的色彩校正算法HM,本文所提方法的PSNR和HSM指标分别提升了4.1%和15.9%,满足了多相机系统在复杂场景下的大视场、高分辨率、无色差的需求。

基于多特征融合的百香果品质识别分类方法

百香果销售需按外观和口感的品质进行分类定价。目前分类主要针对果实外表进行人眼判断,易受视觉疲劳和主观经验影响,缺乏量化标准。基于此种情况提出一种基于机器视觉多特征融合的方法对百香果品质进行自动识别并分类。分别提取百香果的颜色和纹理表观特征进行优化并融合,然后使用SVM分类器对融合特征与果实果糖含量高低进行二分类关联训练和预测。实验结果的分类准确率最高可达到91.48%,表明百香果的外观特征与口感品质有较大的关联性。由此可见采用机器视觉方法对百香果以及其他水果的外观特征进行品质判断具有较高的可行性。其中所使用的算法实现简单,计算速度快,效果良好,具有很大的应用价值。

基于语义和几何一致性的视觉SLAM回环检测算法

回环检测是消除同时定位与地图构建(simultaneous localization and mapping,SLAM)系统中累计误差的关键所在,在光照条件或视角变化较大的情况下,传统的基于外观的回环检测方法往往失效。针对这种情况,在ORBSLAM2的框架基础上提出一种物体级的回环检测方法。利用目标检测获得的语义信息和特征点信息构建物体级语义地图。将语义地图抽象成拓扑图并将地标抽象成节点,用颜色直方图描述节点信息,结合节点间的几何关系,基于语义和几何一致性约束,提出一种图匹配方法实现回环检测。当检测到回环时,通过物体对齐的方式进行回环校正。在公开的TUM和USTC数据集上进行实验,结果表明提出的系统精度较ORBSLAM2平均提高了49.58%,并且构建的语义地图显示出良好的定位效果。

基于空气耦合超声的宣纸润墨性检测技术

宣纸在中国书画艺术历史中占据不可小觑的地位,润墨性是鉴别宣纸质量的重要指标,所以对其润墨性的检测至关重要。现有检测方法易对宣纸造成损坏且受人为主观因素影响较大,为解决现有检测技术的缺陷,该文提出使用空气耦合超声技术对宣纸的润墨性进行检测,针对不同润墨性的宣纸进行C扫描成像,通过彩色直方图分析成像结果中的颜色分布关系,对宣纸润墨性进行评价。当采用400 kHz空耦探头、200 mm/s扫描速度时,C扫描结果均能对不同宣纸的润墨性做出表征,该方法克服传统检测中主观因素的影响,能够在对宣纸无损的情况下实现润墨性检测。通过上述结果表明,该方法可为宣纸的无损检测提供一些理论和实践参考。

面向海岛海岸带区域的高分遥感影像智能化色彩增强方法

原始高空间分辨率海岛海岸带遥感影像往往存在影像灰暗、偏色、地物信息较难辨识的现象。为及时获取清晰、信息丰富、反差适中、亮度均匀的海岛礁遥感影像,满足日益强烈的海岛海岸带地理信息保障需求,针对海岛海岸带高空间分辨率遥感影像,该文提出一种深度学习结合改进直方图匹配的智能化调色方法。首先,进行数据重采样与自适应分块获取抽稀影像;其次,应用MBLLEN网络对抽稀影像进行真彩色增强;最后,采用改进直方图匹配的方法对原始影像进行色彩映射,最终得到符合人眼视觉、色彩一致、细节丰富的遥感影像。采用主客观相结合的方式综合评价调色效果,结果表明:相较于Retinex,HE和MASK等常用调色方法,该文算法结果更符合人眼视觉、色彩一致、细节丰富,可有效改善海岛海岸带高空间分辨率遥感影像视觉效果,较好地保留原始地物的细节信息,大幅提升调色效率。

基于FPGA的仿造数码迷彩生成系统研究

为了解决传统仿造数码迷彩生成算法开发平台灵活性不足的问题,提出了一种基于现场可编程门阵列(FPGA)的仿造数码迷彩生成算法。采用直方图统计提取主要颜色信息,将背景图像马赛克化获得颜色分布信息,依据色差进行主色替换得到仿造数码迷彩的方法,取得了不同主色数量、色差计算权重、颜色量化数量下的数据。结果表明,颜色量化为3600种后,提取出4种主色作为仿造数码迷彩主色,根据色差主色替换时色彩权重3∶6∶1,生成的仿造数码迷彩具有良好的伪装效果,且基于FPGA实现该算法时系统占用资源少,处理800 pixels×480 pixels分辨率的单帧彩色图像所需时间仅为22.21 ms,满足动态场景下生成仿造数码迷彩的实时性需求。该研究为主动伪装技术提供了参考。

Image retrieval based on color features integrated with anisotropic directionality

A novel image retrieval approach based on color features and anisotropic directional information is proposed for content based image retrieval systems （CBIR）. The color feature is described by the color histogram （CH）, which is translation and rotation invariant. However, the CH does not contain spatial information which is very important for the image retrieval. To overcome this shortcoming, the subband energy of the lifting directionlet transform （L-DT） is proposed to describe the directional information, in which L-DT is characterized by multi-direction and anisotropic basis functions compared with the wavelet transform. A global similarity measure is designed to implement the fusion of both color feature and anisotropic directionality for the retrieval process. The retrieval experiments using a set of COREL images demonstrate that the higher query precision and better visual effect can be achieved.

Integrating Color and Spatial Feature for Content-Based Image Retrieval

In this paper, we present a novel and efficient scheme for extracting, indexing and retrieving color images. Our motivation was to reduce the space overhead of partition-based approaches taking advantage of the fact that only a relatively low number of distinct values of a particular visual feature is present in most images. To extract color feature and build indices into our image database we take into consideration factors such as human color perception and perceptual range, and the image is partitioned into a set of regions by using a simple classifying scheme. The compact color feature vector and the spatial color histogram, which are extracted from the seqmented image region, are used for representing the color and spatial information in the image. We have also developed the region-based distance measures to compare the similarity of two images. Extensive tests on a large image collection were conducted to demonstrate the effectiveness of the proposed approach.

基于自适应色彩均衡及改进IBLA的水下图像增强

针对水下环境采集图像和视频存在对比度低、色彩不均衡等颜色失真问题,提出了一种自适应色彩均衡与水下场景深度估计融合的水下图像增强算法。该算法的核心思想由3个步骤组成:首先针对图像色偏严重问题,对色偏严重的通道进行颜色自适应均衡化预处理,以突出纹理特征;其次,根据图像整体的纹理分布特性进行特征提取,并对图像通道进行背景光估计、场景深度估计以及传输系数映射估计;最后,采用场景亮度恢复模型进行特征融合,并基于直方图均衡算法得到水下增强图像。为证明该算法的有效性与先进性,选取真实水下降质图像为处理对象,利用质量评价指标(UIQM)对增强图像进行总体比较。结果表明,该算法有效增强了水下降质图像的清晰度与色彩度,并且清晰地恢复了图像细节。

基于机器视觉的汽车碰撞预警图标识别方法研究

针对汽车碰撞预警测试数据处理耗时长的问题,创新性地将机器视觉应用于汽车碰撞预警系统测试的数据处理。碰撞预警系统测试分为测试阶段和离线数据处理阶段。在测试阶段构建了一种基于颜色直方图相似度局部最小值的方法,以提取关键帧。测试时,首先实时获取帧间颜色直方图相似度序列,然后利用汉宁窗对相似度序列进行平滑处理,最后根据平滑过的帧间相似度局部最小值获取关键帧。在数据处理阶段,人工挑选出一张包含预警图标的图像,并获取图标在图像中的位置。根据尺度不变特征变换特征提取和最快邻近区匹配对局部区域进行特征提取和匹配。试验结果证明,该方法能够实现对汽车碰撞预警图标的快速、有效识别,并输出包含时间信息的关键帧。该方法能提高碰撞预警系统测试数据处理效率、提升自动化程度。

复杂光照环境下的标识线图像增强方法

自动驾驶汽车在行驶过程中需要识别道路标识线以确保行驶在车道上,变电站巡检机器人通过识别道路标识线实现准确巡检。但由于复杂光照环境的影响,道路标识线信息难以准确提取。传统的图像增强方法无法对所有复杂光照环境下的道路标识线图像都产生良好的增强效果,对此提出一种复杂光照环境下的道路标识线图像增强方法。利用HSV色域空间的亮度图像的亮度差进行分层处理,对高亮度差的图像使用自适应伽马校正的方法进行图像增强,对低亮度差的图像先使用直方图锥形拉伸扩大图像灰度级,再利用自适应伽马校正提升图像对比度。实验结果表明,该算法能有效解决低光照、曝光等复杂光照环境所导致的道路标识线难以识别的问题,是一种有效的图像增强方法。

Shape, Color and Texture Based CBIR System Using Fuzzy LogicClassifier

The perfect image retrieval and retrieval time are the two major challenges inCBIR systems. To improve the retrieval accuracy, the whole database is searched basedon many image characteristics such as color, shape, texture and edge information whichleads to more time consumption. This paper presents a new fuzzy based CBIR method,which utilizes colour, shape and texture attributes of the image. Fuzzy rule based systemis developed by combining color, shape, and texture feature for enhanced image recovery.In this approach, DWT is used to pull out the texture characteristics and the region basedmoment invariant is utilized to pull out the shape features of an image. Color similarityand texture attributes are extorted using customized Color Difference Histogram (CDH).The performance evaluation based on precision and BEP measures reveals the superiorityof the proposed method over renowned obtainable approaches.

基于亮度均衡化和仿射变换的交通标志图像修复研究

自动驾驶技术是当前人工智能的研究热点,其中交通标志的正确识别是机器的重要判断依据,但是在自然场景中交通标志图像具有颜色偏差、形状变形、遮挡等一系列问题,导致识别不准确。对于这个问题,提出了亮度均衡化和仿射变化的方法,首先采用HSV颜色空间,提取对应的颜色,再针对亮度信息进行直方图均衡化方法,解决颜色偏差问题,随后使用仿射变换,分别对三角形和圆形的图像进行形状的矫正,并实现背景的去除。实验部分采用占用机器资源较低的HOG+SVM检测方法进行检测,结果表明,和传统的方法相比,该方法在识别率上有20%左右的提升。由此证明,对交通标志图像进行有针对性的修复,对于识别率的提高有着比较大的意义,因为其占用机器资源较低,也给当前深度学习等占用机器资源较多的交通标志识别方法提供了新的思路。

An Image Retrieval Method Based on Color and Texture Features

The technique of image retrieval is widely used in science experiment, military affairs, public security, advertisement, family entertainment, library and so on. The existing algorithms are mostly based on the characteristics of color, texture, shape and space relationship. This paper introduced an image retrieval algorithm, which is based on the matching of weighted EMD（Earth Mover’s Distance） distance and texture distance. EMD distance is the distance between the histograms of two images in HSV（Hue, Saturation, Value） color space, and texture distance is the L1 distance between the texture spectra of two images. The experimental results show that the retrieval rate can be increased obviously by using the proposed algorithm.