基于分割集成的行人检测方法

为提高行人检测的准确率,提出基于分割集成的方法用于静态图片中的行人检测。先将每个训练样本均匀分割成若干区域,提取特征后利用AdaBoost算法对每个区域建立一个局部分类器,这些局部分类器加权组成一个全局分类器。采用不同的分割方法重复上述过程,得到多个全局分类器。为进一步提高检测效果,得到更好的平均性能,对每种分割方法分别使用方向梯度直方图、多尺度方向梯度直方图特征建立2个全局分类器。当检测新的窗口时,集成上述全局分类器,通过加权投票的方式决定最终的检测结果。在INRIA公共测试集上的实验表明,文中方法有效提高检测效果。     

光学显微镜数字化改造的设计及仿真

目前数字显微镜得到了广泛的应用,强大的图像处理功能和友好的用户接口是其主要优势。为了充分利用医学院校的传统光学显微镜,提出了数字化的改造方法。设计出通过CCD采集、DSP图像处理、视频显示的数字化显微图像分析系统仿真平台。并且根据显微图像噪声特点提出分频的对比度受限直方图均衡算法,从而提高图像的对比度,抑制噪声放大。仿真结果表明,硬件平台可以稳定、有效地增强显微图像,并可达到20帧/秒的处理速度。     

基于直方图相似度度量的中央空调风管附尘度检测

对于主从控制中央空调清洁机器人,操作人员依据视频很容易就可判断出风管是否清扫干净。在机器人自主清洗中央空调风管时,为了能够使机器人识别管道内灰尘附着程度,文章采用了直方图相似度作为清洁机器人自动判断管道附尘度和清洁与否的标准。文章给出了相关的原理和算法,并进行了试验验证,结果表明该方法具有快速性、实时性和准确性等特点。     

基于颜色特征的图像检索技术研究

本文针对利用图像的颜色特征丢失空间信息的问题,提出了一种通过提取灰度特征,获取图像的形状特征,综合检索图像的方法。     

实时图像增强算法改进及FPGA实现

针对复杂背景的多目标图像,提出了一种基于直方图的实时自适应图像增强方法.该方法根据自适应直方图窗口选择高低阈值,通过灰度线性变换及灰度级等间距密度均衡进行图像增强.利用该算法增强图像视频时,采用FPGA,通过并行处理结构及流水线技术,可实时处理每秒50帧780×582×12bits的可见光图像.在处理视频的过程中,由前一帧图像的直方图信息,来增强后一帧图像.理论分析和实验结果均表明,该算法克服了直方图均衡及平台直方图均衡增强图像引起的灰度断层现象,有效地增强了图像的对比度,提高了图像质量.     

Image segmentation based on histogram analysis utilizing the cloud model

Both the cloud model and type-2 fuzzy sets deal with the uncertainty of membership which traditional type-1 fuzzy sets do not consider. Type-2 fuzzy sets consider the fuzziness of the membership degrees. The cloud model considers fuzziness, randomness, and the association between them. Based on the cloud model, the paper proposes an image segmentation approach which considers the fuzziness and randomness in histogram analysis. For the proposed method, first, the image histogram is generated. Second, the histogram is transformed into discrete concepts expressed by cloud models. Finally, the image is segmented into corresponding regions based on these cloud models. Segmentation experiments by images with bimodal and multimodal histograms are used to compare the proposed method with some related segmentation methods, including Otsu threshold, type-2 fuzzy threshold, fuzzy C-means clustering, and Gaussian mixture models. The comparison experiments validate the proposed method.     

噪声不敏感的柱状图特征描述符及其在图像检索中的应用

基于内容的图像检索方法往往将图片的内容表示成柱状图,根据图片柱状图之间的相似性进行图片的检索。数码图片中包含的噪声使得柱状图变得平滑,从而使图片之间变得更为相似,这增加了返回结果中包含的图片数量。为了进一步提高图片检索的性能,提出了一种对噪声不敏感的柱状图特征描述符,并应用该特征描述符进行图像之间的相似性匹配。首先将图片中的噪声描述为平稳附加高斯白噪声,并给出了相应的柱状图表示;然后通过随机变量的原点矩定义了柱状图的特征描述符,并分析了如何应用特征描述符恢复原始图片的柱状图。在算法的性能验证过程中,将提出的方法与4种相关算法进行比较,应用两个真实的图片数据库的图像检索实验验证了所提方法的有效性。     

Image contrast enhancement using fuzzy clustering with adaptive cluster parameter and sub-histogram equalization

Histogram equalization is an effective technique to boost image quality and contrast enhancement. However, in some cases the increase in image contrast by traditional histogram equalization exceeds the desired amount Which damages the image properties and wanes its natural look. Histogram division and performing a separate equalization for each sub-histogram is one of the presented solutions. The dividing method and determining the number of sub-histograms are the main problems directly affecting the output image quality. In this study, a method is introduced for automatic determination of the number of sub-histograms and density based histogram division leading to appropriate output with no need for parameter setting. Each main peak is in a separate section. Image contrast is increased with no loss of image specifications through determining the number of sub-histograms based on the number of main peaks. The introduced histogram equalization approach consists of three stages. The first stage, using histogram analysis, produces an automated estimate of number of clusters for image brightness levels. The second, clusters the image brightness levels, and using the provided transfer function, the final stage includes contrast enhancement for each individual cluster separately. The results of the proposed approach demonstrate not only clearer details along with a boost in contrast, but also noticeably more natural appearance in the images.     

铁道钢轨断面的计算机图象处理与仿真

利用计算机图象处理和仿真技术,对铁道钢轨断面进行快速检测与处理的研究。     

动态地构建和维护基于小波的直方图*

利用小波变换的数学理论和方法,对基本的数据分布进行小波分解,在此基础上采用一种新的方法来动态地构建和维护基于小波的直方图,并给出相应的算法。实验证明基于这种方法的小波直方图能提供好的选择性估算和近似技术。