银行币箱字符识别系统的实现

利用数字图像处理技术开发银行币箱自动识别系统。从币箱图像中确定字符位置，提取字符的特征。接着基于Hausdorff距离进行模板匹配，获取冠字、年号和箱号等字符信息。试验结果表明该方案是有效的。     

一种适于串行机实现的图像并行细化算法

为解决现有的图像并行细化算法在串行机上的高效实现问题 ,首先提出了一种 4× 4邻域二值图像的双字节图像编码方案 ,由于在该方案中将每个 4× 4邻域的像素用一个双字节的整数来表示 ,从而将基于整个邻域 16个像素的细化处理转化为一个双字节整数的读、写和比较运算的问题 ;然后在此基础上提出了一种可在串行机上实现的并行细化算法。实验证明 ,该算法适用于当前通用的各种基于模板匹配的并行细化算法 ,其不仅可以取得完全相同的细化结果 ,而且可以大幅度提高图像细化过程在串行机上的执行速度 ;最后简要讨论了该算法利用 PC机中的 MMX技术来进一步提高并行粒度和运算效率方面所具有的潜力     

The impact of new hardware on OCR designs

This paper describes the opportunities available to radically improve the performance cost ratio of OCR machines by taking advantage of new hardware which is either here, or can be made available by inter industry cooperation. Major discussions center around:(1) The page width self-scanned-array (1872 photodiodes) which can be used to greatly reduce the number of mechanical operations needed to scan a multi-line document: (2) The much reduced cost of semiconductor memory (particularly the charge coupled devices) which allows the use of memory to eliminate double scanning as well as other awkward and embarrassing operations: (3) A proposal for an LSI correlator which can provide substantial gains in all performance and cost categories, as well as providing prospects for the modest application of developments in learning theory. The leadership to provide such a correlator may have to spring from the OCR industry, including agreement on certain standards.     

利用自适应时间片梯度谱对镜头转换进行精细识别

提出了一种利用视频序列的自适应时间片梯度谱对镜头转换类型进行精细识别的算法 .在这个算法中 ,首先提出了自适应时间片梯度谱的概念 ,并且在此基础上 ,提出了用于识别镜头转换类型的模板构造和匹配算法 ,同时还给出了一种描述语言作为模板的软描述方法 ,用以适应不同的图象尺寸和镜头转换的持续时间 .实验结果表明 ,这种方法在多数情况下具有很好的识别效果 ,只是在两个镜头转换非常相近时 ,识别效果差些 ,另外 ,该方法识别速度快 ,同时具有很强的鲁棒性和可扩展性 ,是解决镜头转换类型精细识别问题的一个有益尝试     

Research on a face recognition system by the genetic algorithm

Computer vision and recognition is playing an increasingly important role in modern intelligent control. Object detection is the first and most important step in object recognition. Traditionally, a special object can be recognized by the template matching method, but the recognition speed has always been a problem. In this article, an improved general genetic algorithm-based face recognition system is proposed. The genetic algorithm (GA) has been considered to be a robust and global searching method. Here, the chromosomes generated by GA contain the information needed to recognize the object. The purpose of this article is to propose a practical method of face detection and recognition. Finally, the experimental results, and a comparison with the traditional template matching method, and some other considerations, are also given. This work was presented in part at the 11th International Symposium on Artificial Life and Robotics, Oita, Japan, January 23–25, 2006     

基于肤色与模板匹配的人脸检测方法研究

利用肤色信息在彩色图像中检测人脸速度快、易于实现,但准确率不高。本文提出首先应用人脸肤色信息在彩色图像中进行人脸粗略检测,得到候选人脸区域,再以基于梯度模板匹配的方法进行人脸精确定位,从候选区中准确地找到人脸。将这两种方法结合在保证精确的人脸检测的前提下,可有效提高检测速度。     

Inter-image outliers and their application to image classification

Image variability that is impossible or difficult to restore by intra-image processing, such as the variability caused by occlusions, significantly reduces the performance of image-recognition methods. To address this issue, we propose that the pixels associated with large distances obtained by inter-image pixel-by-pixels comparisons should be considered as inter-image outliers and should be removed from the similarity calculation used for the image classification. When this method is combined with the template-matching method for image recognition, it leads to state-of-the-art recognition performance: 91% with AR database that includes occluded face images, 90% with PUT database that includes pose variations of face images and 100% with EYale B database that includes images with large illumination variation.     

Using selective correlation coefficient for robust image registration

A new method is proposed for robust image registration named Selective Correlation Coefficient in order to search images under ill-conditioned illumination or partial occlusion. A correlation mask-image is generated for selecting pixels of an image before matching. The mask-image can be derived from a binary-coded increment sign-image defined from any object-image and the template. The mask-rate of occluded regions is theoretically expected to be 0.5, while unoccluded regions have much lower rate than 0.5. Robustness for ill-conditioned environment can be realized since inconsistent brightness of occluded regions can be omitted from the mask operation. Furthermore, the mask enhancement procedure is proposed to get more stable robustness. The effectiveness of masking increases by the procedure, resulting in the rate around 0.7 for masking of occluded regions. This paper includes a theoretical modeling and analysis of the proposed method and some experimental results with real images.     

An Approach for Recognition and Interpretation of Mathematical Expressions in Printed Document

In this paper, we propose an approach for understanding Mathematical Expressions (MEs) in a printed document. The system is divided into three main components: (i) detection of MEs in a document; (ii) recognition of the symbols present in each ME; and (iii) arrangement of the recognised symbols. The MEs printed in separate lines are detected without any character recognition whereas the embedded expressions (mixed with normal text) are detected by recognising the mathematical symbols in text. Some structural features of the MEs are used for both cases. The mathematical symbols are grouped into two classes for convenience. At first, the frequently occurring symbols are recognised by a stroke-feature analysis technique. Recognition of less frequent symbols involves a hybrid of feature-based and template-based technique. The bounding-box coordinates and the size information of the symbols help to determine the spatial relationships among the symbols. A set of predefined rules is used to form the meaningful symbol groups so that a logical arrangement of the mathematical expression can be obtained. Experiments conducted using this approach on a large number of documents show high accuracy.     

On-line signature recognition based on VQ-DTW

This paper studies some pattern recognition algorithms for on-line signature recognition: vector quantization (VQ), nearest neighbor (NN), dynamic time warping (DTW) and hidden Markov models (HMM). We have used a database of 330 users which includes 25 skilled forgeries performed by five different impostors. This database is larger than the typical ones found in the literature.Experimental results reveal that our first proposed combination of VQ and DTW (by means of score fusion) outperforms the other algorithms (DTW, HMM) and achieves a minimum detection cost function (DCF) value equal to 1.37% for random forgeries and 5.42% for skilled forgeries. In addition, we present another combined DTW-VQ scheme which enables improvement of privacy for remote authentication systems, avoiding the submission of the whole original dynamical signature information (using codewords, instead of feature vectors). This system achieves similar performance than DTW.     

基于多模板匹配的单人脸检测

提出了一种基于多模板匹配的一般环境图象中单人脸的检测方法。首先用双眼模板初步筛选,然后使用具有不同长宽比的多个人脸模板进行检测和定位,最后利用有脸器官的边缘特征进行确认。采用比固定比率压缩输入图象的方法解决不同尺度有脸的检测问题。实验表明这种方法具有较高的速度和检测成功率。     

基于高斯模型的污损纸币识别算法研究

研究纸币识别问题,提高纸币识别的准确率。针对纸币识别过程中,当待识别的纸币在流通中存在被污染或者磨损,传统的模板匹配的识别算法受纸币污损的影响识别的准确性。为解决上述问题提出一种高斯模型的识别算法,首先对待检测图像进行亮度补偿、边缘检测、倾斜校正等预处理,然后将图像划分为若干个矩形子区域,计算各子区域的灰度平均值作为提取的图像初始特征,通过计算初始特征的先验概率并对后验概率进行修正,对污损区域特征值的校正,最后建立高斯模型完成纸币的识别,克服了传统无法准确识别污损纸币的问题。实验证明,改进方法能够将纸币污损部分校正并将纸币准确识别,取得了满意的效果。     

栅格地图识别的专家系统模型

数据获取是ＧＩＳ的基本组成部件。地图数据依然是大多数ＧＩＳ的主要数据源。如何实现地图数据的快速转换已成为ＧＩＳ迅速发展的一个“瓶颈”。本文基于对地图识别所需知识种类、目标符号描述模型、知识表示方法及知识利用机制的详细研究，提出了一个栅格地图识别的专家系统模型。     

一种改进的指纹图像细化算法

在自动指纹识别系统中,细化占有重要的地位,现有的指纹细化算法存在很多问题,如细化不彻底、纹线吞噬、骨架偏离纹线中心等。对快速细化算法和改进的OPTA细化算法进行了分析和研究,指出这两种算法在指纹纹线和分叉点处图像细化不彻底等缺陷。同时将两种细化算法有机结合,设计了一组改进的细化模板,提出了一种新的细化算法。实验结果证明：该算法与传统的细化算法相比没有破坏纹线的连接性,不会引起纹线的逐步吞食,又保护了指纹的细节特征。而且该算法运算速度也大大加快,处理后的指纹图像细化完全,骨架接近纹线中心线,光滑无毛刺,方便特征提取和减少匹配的复杂度。     

经典边缘检测的快速算法

边缘检测是图像处理的重要步骤，在许多实际应用中检测速度是至关重要的。本文在分析传统经典边缘检测算子内在结构的基础上，提出了一种有效的快速算法，实验表明随着图像尺寸的增大，该算法可比经典计算方法快10倍以上。     

一种基于特征匹配的人脸配准判断方法

现有的人脸识别应用系统大都忽略了人脸配准的检查,造成"误配准灾难",导致识别性能下降。因此,对规格化后的人脸图像进行判断筛选,以保证只有正确配准的人脸图像才能用于后续识别。选用一定数量正确配准的规格化人脸图像平均值作为标准人脸,用SIFT关键点定位方法得到标准人脸的多个关键点,采用分块的梯度方向直方图统计方法提取关键点的邻域图像特征;然后,将标准人脸的关键点位置作为待检测人脸的定位点,用同样的方法提取定位点的邻域图像特征;计算待检图像与标准人脸图像对应关键点的特征矢量相似度,设定合理阈值判断待检测图像是否配准。实验证明,该方法能有效去除误配准人脸图像,有利于提高人脸识别系统的可靠性。     

基于信息增益的Web人物关系抽取*

针对人物关系抽取中的效率与准确性问题进行了研究,提出一种基于信息增益的轻量级Web人物社会关系提取方法。它通过计算初始关系元组的关系描述词的信息增益值进而确定元组上下文位置并据此创建相应的关系抽取模板,最后利用模板实现了Web的人物关系自动提取。针对中文语义上存在相似性的问题,引入了基于《同义词词林》与基于《知网》的人物关系描述词扩展方法。对于某一句子内包含多个人物实体且存在多种人物关系的情况,提出了一种基于模板上下文信息增益值模糊匹配的方法来抽取符合特定人物关系的人物实体。实验结果证明：该方法的平均准确率为89.92%,平均召回率为84.64%。基于信息增益的Web社交网络人物关系抽取方法能有效地完成实时语料中的关系抽取任务。     

基于最大熵的哈萨克语词性标注模型

最大熵模型能够充分利用上下文,灵活取用多个特征。使用最大熵模型进行哈萨克语的词性标注,根据哈语的粘着性、形态丰富等特点设计特征模板,并加入了向后依赖词性的特征模板。对模型进行了改进,在解码中取概率最大的前n个词性分别加入下一个词的特征向量中,以此类推直至句子结束,最终选出一条概率最优的词性标注序列。实验结果表明,特征模板的选择是正确的,改进模型的准确率达到了96.8%。     

基于特征提取和匹配的图像倾斜校正算法

针对图像中不包含明显直线的情况,提出一种基于特征点提取的图像倾斜校正算法。该算法建立在与无倾斜的训练图像比对基础上,利用特征点构造直线,不依赖于原图中是否存在直线进行倾斜检测,具有尺度、平移无关性。使用双向最大相关系数匹配,匹配正确率较高。利用大数原理对数据进行处理,去除误匹配的影响。该算法最少可以利用两个匹配对,检测出图像倾斜角度。结合本文的应用背景,本文还设计了一种用于特征提取的圆形模板,具有类似于旋转不变的性质。     

基于信息熵的子图匹配算法

子图查询是指输入一个图数据库和查询子图,输出图数据库中包含查询子图的图集合,它广泛应用于社会网、生物网和信息网的查询应用中。目前的子图查询算法大多采用静态消耗测算模式,此类测算模式在图中点数和连接边数呈指数分布时,会在少数节点上花费较多时间遍历其邻节点,导致查询算法效率低下。根据信息熵在信息度量中的作用,将条件信息熵作为启发式匹配的依据,提出了基于信息熵的子图匹配算法。实验表明,基于信息熵的子图匹配算法具有更高的查询效率,且在指数分布的数据集上效果更明显。