基于支持向量机的手写体数字识别系统设计

数字识别是光学字符识别技术里发展比较早的一种技术,是OCR的一个分支。数字识别又分为手写数字识别和非手写数字识别,提到的手写数字识别是指脱机手写数字识别。支持向量机是近几年来模式识别领域中的一个新技术,它被广泛应用到文字识别、人脸识别等应用中,是模式识别领域中的研究热点,把支持向量机技术应用到手写数字识别系统中,以期提高识别系统的性能。     

Segmentation of connected handwritten numeral strings

A new approach to separating single touching handwritten digit strings is presented. The image of the connected numerals is normalized, preprocessed and then thinned before feature points are detected. Potential segmentation points are determined based on decision line that is estimated from the deepest/highest valley/hill in the image. The partitioning path is determined precisely and then the numerals are separated before restoration is applied. Experimental results on the NIST Database 19, CEDAR CD-ROM and our own collection of images show that our algorithm can get a successful recognition rate of 96%, which compares favorably with those reported in the literature.     

改进主曲线及在手写体数字骨架化中应用研究

针对主曲线算法初始化步骤效果差,导致后面所得结果不能正确反映数据的拓扑结构,对其进行改进,用连通k近邻代替第一主成分线找到数据的初始拓扑结构。将改进后的算法应用于脱机手写体数字骨架化,实验证明改进的算法克服了上面提到的缺点,能更好的找到数据的拓扑结构,在时间复杂度、连通性、参数等各方面都优于其他改进算法。改进算法适于具有“连通性”的数据。     

Web mining based on Growing Hierarchical Self-Organizing Maps: Analysis of a real citizen web portal

This work is focused on the usage analysis of a citizen web portal, Infoville XXI (http://www.infoville.es) by means of Self-Organizing Maps (SOM). In this paper, a variant of the classical SOM has been used, the so-called Growing Hierarchical SOM (GHSOM). The GHSOM is able to find an optimal architecture of the SOM in a few iterations. There are also other variants which allow to find an optimal architecture, but they tend to need a long time for training, especially in the case of complex data sets. Another relevant contribution of the paper is the new visualization of the patterns in the hierarchical structure. Results show that GHSOM is a powerful and versatile tool to extract relevant and straightforward knowledge from the vast amount of information involved in a real citizen web portal.     

Segmentation and recognition of handwritten dates: an HMM-MLP hybrid approach

This paper presents an HMM-MLP hybrid system for segmenting and recognizing complex date images written on Brazilian bank checks. Through the recognition process, the system makes use of an HMM-based approach to segment a date image into subfields. Then the three obligatory date subfields (day, month, and year) are processed. A neural approach has been adopted to decipher strings of digits (day and year) and a Markovian strategy to recognize and verify words (month). The final decision module makes an accept/reject decision. We also introduce the concept of metaclasses of digits to reduce the lexicon size of the day and year and improve the precision of their segmentation and recognition. Experiments show interesting results on date recognition.Received: 17 December 2002, Accepted: 16 July 2003, Published online: 17 November 2003Correspondence to: Marisa Morita     

GEP在数字图像分割中的应用

基因表达式程序设计（简称GEP）是一种新型的遗传算法，它继承了遗传程序设计（简称GP）和遗传算法（简称GA）的优点并且具有更高效和更强的搜索能力，它是借鉴生物选择和进化机制发展起来的一种高度并行、随机、自适应的搜索算法。特别适合于处理传统搜索算法解决不好的复杂的和非线性问题。本文将在系统介绍表达式程序设计的基本理论基础上．介绍其在数字图像分割中的应用。     

一种改进的期望最大图像分割方法

期望最大算法是进行极大似然估计的一种有效方法,它主要用于观测数据不完全或者似然函数不是解析时的参数估计。文中提出了一种期望最大化和贝叶斯信息准则相结合的图像分割方法。首先,运用K均值方法初始化图像分布;然后,运用期望最大算法估计输入图像参数数据,图像中类的数目由贝叶斯消息准则自动确定;最后,运用最大似然标准将像素归类于最相近的类中。实验中将此方法用于对葡萄叶部病害彩色图像的分割,其结果表明此方法有效。     

Neocognitron with improved bend-extractors: Recognition of handwritten digits in the real world

We have reported previously that the performance of a neocognitron can be improved by a built-in bend-extracting layer. The conventional bend-extracting layer can detect bend points and end points of lines correctly, but not always crossing points of lines. This paper shows that an introduction of a mechanism of disinhibition can make the bend-extracting layer detect not only bend points and end points, but also crossing points of lines correctly. This paper also demonstrates that a neocognitron with this improved bend-extracting layer can recognise handwritten digits in the real world with a recognition rate of about 98%. We use the technique of dual thresholds for feature-extracting S-cells, and higher threshold values are used in the learning than in the recognition phase. We discuss how the threshold values affect the recognition rate.     

一种基于连通域标记的矿井巷道灯识别方法

针对本次项目中每帧视频图像中出现多个矿井巷道灯区域和标示牌区域,提出一种基于连通域标记的矿井巷道灯识别方法。此算法能很好地标记出图像的所有连通区域,并且通过计算各个连通区域的面积特征,很好地把目标识别出来,为下一步机车定位与跟踪打下了基础,此算法满足实时性要求。     

一种基于连通域标记的矿井巷道灯识别方法

针对本次项目中每帧视频图像中出现多个矿井巷道灯区域和标示牌区域．提出一种基于连通域标记的矿井巷道灯识别方法。此算法能很好地标记出图像的所有连通区域．并且通过计算各个连通区域的面积特征,很好地把目标识别出来,为下一步机车定位与跟踪打下了基础,此算法满足实时性要求。     

一种对光照具有鲁棒性的图像分割方法

研究了灰度图像的OTSU(最大类间方差)自动阈值分割法。OTSU方法作为一种单一阈值的分割方法,当图像受光照和反射光等的影响明显时,将会出现严重的误分割现象。考虑到OTSU方法的最大类间方差化的思想,根据灰度图像的像素点灰度的直方图分布、空间分布,提出了一个新的分割阈值方法。先根据OTSU方法的特点自设计一个函数,对图像进行变换,以便后面的处理,再对其图像以改进的OTSU方法进行分割。通过对化学实验中两种液体的拍摄图片及数字图像处理中标准图片进行试验,理论分析与实验结果表明：该方法能够对受光照及反射光影响大的图像实现正确的分割,将目标图像清晰地从背景中分割出来。     

Adjacency stable connected operators and set levelings

This paper studies morphological connected operators. Particularly, it focuses on an adjacency constraint, as well as on the so-called set levelings. Some important findings are reported in this work. First, the relationships between the so-called adjacency stable operators and set levelings are investigated, and an equivalence is established. This permits to apply some properties to the related operator class. Second, the implications and limits of a property presented elsewhere that states that certain connected operators can be expressed as a sequential composition of an opening and a closing (and vice-versa) based on markers are treated. Then, a commutative property that involves alternated attribute filters is presented. In addition, other related expressions are discussed.     

基于SOM网络的语音训练可视化方法研究

提出了一种利用SOM网络输出层可视化的特点进行语音训练的方法。SOM网络能够将输入向量映射到二维平面或曲面上,受试者通过视觉反馈的位置信息,指导其发音行为。为了提高SOM聚类效果,SOM还进行加强训练;讨论了SOM输出层神经元个数对聚类的影响。实验结果表明,提出的利用SOM语音训练方法,直观简单,能够有效地实现“看图说话”。     

支票大写金额图像分割策略

字符图像的分割是票据自动处理系统中一个预处理过程,提取字符的质量对识别系统有很大的影响。我国支票大写金额图像背景中存在定位线和背景纹理,还有各式各样的印章对笔画信息的干扰。该文解决了复杂背景下二值化问题,采用形态学方法去除定位线,根据目标与背景的灰度和双边缘特征分析进行二值化处理,利用用户填写字符串时的书写习惯去除孤立印章碎块,基于区域增长的后处理过程来修补前期处理过程中断裂的笔画。该方法在真实支票图像的获取上,取得了较为满意的结果。     

显微细胞图像的自动分割

由于细胞组织本身的复杂特性以及显微镜的影响,细胞图像的分割成为图像分割中的一大难题,考虑到边缘检测可以准确的为分割提供边缘点,提出了基于区域一致性测度的边缘检测算法,针对细胞图像的特点,实现其初始轮廓的自动获取,运用活动轮廓模型对初始轮廓进行优化,从而达到在大样本条件下直接对彩色细胞图像自动分割的目的。     

基于小区域增长的MDCT图像分割

提出了一种基于小区域增长的分割算法对人体肝脏的MDCT医学图像进行分割。先把三维人体肝脏的MDCT图像变成一系列二维图像;再对每个二维图像分配多个种子点,从每个种子点出发进行小区域增长;最后,把每个二维图像分割的结果整合成三维肝脏图像。实验结果表明了该算法的准确性和可行性。     

A criterion based on Fourier transform for segmentation of connected digits

Abstract. Segmentation is the most difficult problem in handwritten character recognition systems and often causes major errors in performance. To reach a balance between speed and accuracy, a filter distinguishing connected images from isolated images for multiple stage segmentation is required. The Fourier spectrum is a promising approach to this problem, although it suffers from the heavy influence of stroke width. Therefore, we introduce SFS (SFS) to eliminate the stroke-width effect. Based on the SFS, a set of features and a fine-tuned criterion are presented to classify connected/isolated images. Theoretical analysis demonstrates their soundness, while experimental results demonstrate that this criterion is better than other methods. Received February 18, 2000 / Revised June 3, 2000     

支票中手写体数字串的提取与分割

设计了支票小写金额自动识别系统的前期处理模块,包括手写数字串的提取与分割。在数字串的提取过程中,首先采用动态阈值选取算法去除图像中的背景底纹,然后设计专门的线检测与去除过程去除定位格线;再利用检测到的框线位置将图像分块,根据目标的大小选取合适的阈值去除印章图像;最后采用连通区分析的方法提取数字串。在数字串的分剖过程中,结合了定位格的位置信息,简化了分割过程。该文提出的方法在现行支票图像上获得了较为满意的结果,基本达到了实用的水平。     

手背静脉图像分割及细化算法研究

手背静脉识别技术通常基于静脉纹路的细节特征点对个人身份进行验证。为了准确地提取出手背静脉纹路中的细节特征点,提取手背静脉图像中的有效区域并对其进行归一化、增强和去噪处理．分别采用局部最大类间方差法（OSTU）、阈值图像法和NiBlack法对图像进行分割,分别采用Hilditch算法、快速细化算法、Zhang＆Suen算法和OPTA算法对分割后得到的二值图像进行细化以获取静脉纹路。实验结果表明,基于合理的参数,NiBlack法和Hilditch算法分别取得较好的分割与细化处理结果。