静脉灰度图像拓扑特征提取方法

二值化处理作为静脉识别中关键步骤不可避免会造成特征信息的部分减损,为了克服这种情况,文中提出一种跳过二值化过程直接对静脉灰度图像进行拓扑特征提取的新方法,该方法首先根据像素的邻域信息计算图像的方向场极值图(EGDF,extreme graph of direc tional fields),并利用预先定义的约束模板集从EGDF中逐步提取出静脉主脊,然后在设定的范围约束图中,利用最大邻域点跟踪算法从静脉主脊的各个端点开始搜索从而获得静脉次脊,最后由静脉主脊和静脉次脊组成了静脉灰度图像的全部拓扑特征.通过对比实验,发现文中算法提取的静脉拓扑特征优于常规组合方法即二值化后再进行骨架提取得到的静脉拓扑特征,且克服了基于新小波函数的对称分析法中无法提取漂浮静脉纹路以及将两条相距较近的纹路误识为一条纹路的问题.因此,是一种有效的静脉灰度图像拓扑特征提取方法.     

Direct gray-scale extraction of features for character recognition

A method for feature extraction directly from gray-scale images of scanned documents without the usual step of binarization is presented. This approach eliminates binarization by extracting features directly from gray-scale images. In this method, a digitized gray-scale image is treated as a noisy sampling of the underlying continuous surface and desired features are obtained by extracting and assembling topographic characteristics of this surface. The advantages and effectiveness of the approach are both shown theoretically and demonstrated through preliminary experiments of the proposed method     

基于小波调制尺度的语音特征参数提取方法

时频分析的理论基础上,提出了一种基于小波调制尺度特征的参数提取方法。根据人对调制谱信息的感知特性及干扰在调制谱中的特点,采用小波分析技术及归一化处理求得归一化的小波调制尺度特征参数,并以此作为语音的动态特征应用于语音识别系统。通过与MFCC一阶、二阶系数对比的汉语音节识别实验表明,该方法在抗噪声干扰和说话速率变化等方面比MFCC的一阶、二阶系数的性能优越,为提高语音识别鲁棒性提供了一种新途径。     

An evaluation of parallel thinning algorithms for characterrecognition

Skeletonization algorithms have played an important role in the preprocessing phase of OCR systems. In this paper we report on the performance of 10 parallel thinning algorithms from this perspective by gathering statistics from their performance on large sets of data and examining the effects of the different thinning algorithms on an OCR system     

SOM Segmentation of gray scale images for optical recognition

This paper describes a clustering technique using Self Organizing Maps and a two-dimensional histogram of the image. The two-dimensional histogram is found using the pixel value and the mean in the neighborhood. This histogram is fed to a self organizing map that divides the histogram into regions. Carefully selecting the number of regions, a scheme that allows an optimum optical recognition of texts can be found.

The algorithm is specially suited for optical recognition application where a very high degree of confidence is needed. As an example application, the algorithm has been tested in a voting application, where a high degree of precision is required. Furthermore, the algorithm can be extended to any other thresholding or clustering applications.     

煤与矸石图像灰度信息和纹理特征的提取研究

针对现有大多数煤与矸石图像识别方法只单一地利用灰度均值和灰度方差进行识别,存在识别准确度和效率不高等问题,提出了一种煤与矸石图像灰度信息和纹理特征提取方法。该方法提取具有代表性的特征参数,如灰度均值、平滑度及灰度共生矩阵的能量、对比度、相关性、熵等,作为识别煤与矸石的重要依据。Matlab仿真分析结果表明,以上特征参数可以有效地描述煤与矸石的图像特征,可为煤与矸石的自动识别与分选提供重要参考依据。     

新的噪声污染灰度图像边缘检测方法

传统的图像边缘检测方法由于引入了各种微分运算,因此用于噪声图像边缘检测时对噪声极度敏感。针对这一问题,提出了一种基于独立分量分析技术的噪声图像边缘检测方法,该算法通过计算数据之间的高阶统计信息,提取特征模板,然后将被高斯噪声污染的灰度图像与这些模板逐个匹配,提取出边缘成分。实验结果表明,基于独立分量分析技术的模板匹配方法自适应强,复杂度低,是一种有效的高斯噪声污染灰度图像边缘检测方法。     

显著度可控的DEM地形特征线提取

目的 基于数字高程模型（DEM）的地形山脊线和山谷线提取对地形模型简化、基于样本的地形合成和地形地貌研究有重要意义,针对许多传统算法无法对所提取特征线的显著度进行方便准确的控制,以及不支持环形特征线提取的问题,提出一种新的显著度可控的DEM地形特征线提取算法。方法 首先利用全局断面扫描算法提取特征点并计算各特征点的显著度,然后根据特征点的特征方向进行特征延伸以增强特征连通性,接着采用改进的Hilditch细线化算法对特征点集合进行细线化处理,之后为相邻特征点添加特征边,构成特征图,利用环路检测与破环算法检测特征图中的环路,并破除冗余小环路,最后根据分支显著度的相似度和分支方向一致性进行特征图分解,计算分解得到特征线的显著度并筛选得到最终特征线。结果 使用真实DEM数据提取最显著的若干条特征线,与现有的基于特征显著度的地形特征线提取算法进行对比,本文算法对特征图的分解能够更准确地提取主干特征线,而基于显著度的特征线筛选控制也更加准确合理。对提出的环路检测与破环算法进行实验验证,该算法能保留大的山脊线环路,破除小的冗余环路。结论 实验结果表明,本文算法能有效实现显著度可控的山脊线和山谷线自动提取,提取结果与人眼观察结果基本一致,同时能够支持含有环形特征的地形。     

新的噪声污染灰度图像边缘检测统计方法*

针对传统算子进行边缘检测时易丢失边缘信息和在非边缘处增强噪声的缺陷,提出一种基于非参数变点统计分析的噪声图像边缘检测方法,该统计方法不但不需要图像数字特征的任何先验信息,而且对噪声污染的图像不作任何滤波处理.实验结果表明,提出的算法优于Sobel算子,并能抑制信噪较低的高斯噪声和密度较高的椒盐噪声对分割结果的影响,是一种有效的噪声污染灰度图像边缘检测方法.     

Image approximation from gray scale ``medial axes''

Several types of gray-weighted ``medial axes' have been defined. This paper shows that one of them, the min-max medial axis, can be used to reconstruct good approximations to the original image based on a relatively small amount of information.     

Perceptual analysis of gray and color scale measurements

Recently, the gamma subcommittee of the International Committee for Display Metrology has adopted various gamma measurement methods in Information Display Measurements Standard. This article describes further tests including perceptual verification of the suggested measurement methods. In order to verify the suggested measurement method, visual assessment has been carried out. The results of visual assessment can be applied to provide gamma distortion threshold values of the suggested metrology in Information Display Measurements Standard.     

Fault features extraction for bearing prognostics

Over the past years, investigation on condition-based maintenance (CBM) technique on bearing has been conducted. Bearing diagnostics and prognostics are the important aspects in CBM. A key to the success of using vibration data for bearing fault diagnostics and bearing lifecycle prognostics is a quantified relationship between bearing damage and bearing fault features. To establish such a quantitative relationship, effective signal processing techniques to extract bearing fault features from vibration signals are needed. This paper describes a newly developed fault feature extraction method for bearing prognostics. The effectiveness of the method is demonstrated with two real bearing run-to-failure test datasets: one collected under normal operating conditions and another one under abnormal operating conditions. Experimental results show that the bearing fault features extracted using both traditional vibration analysis methods and the proposed method give clear bearing heath degradation trend for the dataset collected under normal operating conditions. However, for the data collected under abnormal operating conditions, bearing fault features obtained using traditional vibration analysis methods fail to show the bearing health degradation trend while the fault features extracted using the proposed method give consistent bearing degradation trends.     

MGSI-8CA标记算法

针对已有连通域标记算法不能适用于遥感数据等海量灰度图像八连通域快速标记的问题,设计并实现了一种MGSI-8CA标记算法。该算法对传统的八连通域标记算法进行八向变四向优化,采用列表机制解决连通域标记冲突问题,并引入了筛选机制和分块处理机制,实现了对海量灰度图像八连通域标记的快速处理,同时也得到了灰度图像连通域的正确划分及精确的连通域数目。实验结果证明,MGSI-8CA标记算法运行效率高,更能适应海量灰度图像处理的要求。     

对图像灰度级分段的压缩编码

给出了一种新的无损压缩图像的编码方法。利用图像相邻像素点的灰度级连续和集中的特点，对灰度级进行分段编码，并用MATLAB编程实现，取得了很好的效果。其实验结果与哈夫曼编码做了比较，经过分析，此编码方法在灰度级概率均匀分布时具有优势。     

Integrated text and line-art extraction from a topographic map

Our proposed approach to text and line-art extraction requires accurately locating a text-string box and identifying external line vectors incident on the box. The results of extrapolating these vectors inside the box are passed to an experimental single-font optical character reader (OCR) program, specifically trained for the font used for street labels. In the first evaluation experiment, automated techniques are used to identify the boxes and the line vectors. In the second, more comprehensive, experiment an operator marks these using a graphical user interface. OCR results on 544 instances of overlapped street-name boxes show the following improvements due to the integrated processing: the error rate is reduced from 4.1% to 2.0% for characters and from 11.8% to 6.4% for words.