一种斜体印刷字倾斜角度检测算法

斜体印刷字倾斜校正是光学字符识别中字符列切割的重要步骤,为了解决传统算法难以满足字符多样性等问题,提出了一种新的斜体印刷字倾斜角度检测算法.算法将文本行中所有斜体字看成一个整体,首先采用水平模糊去除字符多样性影响的同时保留足够多的倾斜角度信息,再通过垂直投影统计分析测得倾斜角度,从而实现斜体印刷字的倾斜检测与校正.理论分析及仿真结果表明,算法对中文、英文、数字及不同字体的倾斜字符均有效,测角正确率高、计算量小,具有良好的应用前景.     

基于类内均值的双投影2DPCA人脸识别方法

在人脸识别问题中,如何提取具有鲁棒性的人脸特征和降低特征维数是两个关键。根据二维主成分分析方法直接利用二维图像来构建方差矩阵的优点,引入了类内均值的思想,首先计算每类训练样本的类内平均脸,并用它对各类样本进行规范化处理,有效扩大了类间样本的差别,缩小了类内样本的差别,进行协方差矩阵的计算并提取最优投影特征向量进行人脸图像的特征提取,通过在水平和垂直两个方向上顺序执行两次提取和投影的操作,极大压缩了特征的维数,克服了传统二维主成分算法的不足。在人脸库ORL和Yale的试验对比结果表明,方法对光照与表情变化有较好的鲁棒性,能实现较高的识别率,因此在实际中具有一定的应用意义。     

基于免疫和模糊模式识别的检测器生成模型

分析了在检测器生成过程中引入模糊模式识别的原因,提出了一种基于免疫原理和模糊模式识别的检测器生成模型,该模型的核心算法是基于隶属度的检测器选择算法.详细描述了该算法的算法流程和检测器对非我抗原集合隶属度的计算算法,并简述了初始检测器生成算法和分层检测策略.设计了仿真试验,并将实验结果同传统方法进行了比较,详述了仿真实验中各个参数选择的依据和理由,试验结果表明新模型呈现较高的检测率和低的误检率.     

应用分类器组合模型进行岩性识别

为了达到应用模式识别对储层岩性进行准确的识别,根据不同性质分类器的组合可以较全面描述一个模式从而降低识别错误及增强识别鲁棒性这种特性,结合模糊数学中的隶属度实现了多个分类器的定量组合.应用了几种不同的分类器进行组合,同时应用某油田的岩性识别作为实例进行验证,并与单个分类器进行比较,结果表明在间等条件下组合分类器的性能要比单个分类器的性能要好得多.这说明了应用不同性质的分类器进行组合识别的分类方法足可行性和有效性.     

基于图像质量分区的指纹特征提取

低质量指纹图像的特征提取和变形指纹的匹配是当前指纹识别研究中的两个主要问题。很多算法在特征提取时不区分高、低质量区域,结果在高质量区域耗费了过多的运算时间和计算资源。本文提出了一种基于图像质量分区的指纹特征提取方法,先用一种简单的图像区域质量计算方法评价各区域的图像质量,然后对高质量区域直接从灰度图像跟踪纹线、提取节点,对低质量区域执行传统的方向计算、增强、二值化和细化后提取特征。实验结果表明,该方法不仅提高了特征提取的速度,在准确性上也有所提高。     

Finding the number of clusters in ordered dissimilarities

As humans, we have innate faculties that allow us to efficiently segment groups of objects. Computers, to some degree, can be programmed with similar categorical capabilities, which stem from exploratory data analysis. Out of the various subsets of data reasoning, clustering provides insight into the structure and relationships of input samples situated in a number of distributions. To determine these relationships, many clustering methods rely on one or more human inputs; the most important being the number of distributions, c, to seek. This work investigates a technique for estimating the number of clusters from a general type of data called relational data. Several numerical examples are presented to illustrate the effectiveness of the proposed method.     

An FPGA-based face recognition using combined 5/3 DWT with PCA methods

This paper describes a new scheme for feature extraction from facial images on FPGA. The proposed method is comprised of two stages. The first stage uses the 5/3 DWT to decompose the original face image into LL, LH, HL, and HH wavelet coefficient to reduce the size of the image. In the second stage, PCA is employed to extract the face features from the wavelet coefficients. Here we use the power iteration algorithm to find the eigenvector of the covariance matrix. We present an efficient hardware architecture using combination of parallel processing module and serial processing module. This method can take the benefits of parallel usage advantage of FPGAs and can save hardware resources. Complete hardware implemented on a Stratix II FPGA. The experimental results show that the system works with high processing rate and only 21% of the logic resources an FPGA are consumed by face recognition logic Thus it is very suitable for the low cost implementation of the face recognition system.     

Face detection and recognition of natural human emotion using Markov random fields

This paper presents an integrated system for emotion detection. In this research effort, we have taken into account the fact that emotions are most widely represented with eye and mouth expressions. The proposed system uses color images and it is consisted of three modules. The first module implements skin detection, using Markov random fields models for image segmentation and skin detection. A set of several colored images with human faces have been considered as the training set. A second module is responsible for eye and mouth detection and extraction. The specific module uses the HLV color space of the specified eye and mouth region. The third module detects the emotions pictured in the eyes and mouth, using edge detection and measuring the gradient of eyes’ and mouth’s region figure. The paper provides results from the system application, along with proposals for further research.     

人脸检测方法综述

人脸检测问题的提出是为了在自动人脸识别系统中的定位,近年来,由于其在安全控制、人机界面、视觉监测、基于内容的检索等领域的应用价值,开始作为一个独立的课题受到研究者的普遍重视。该文从人脸检测的模式、人脸特征的提取、人脸特征的综合、评估标准等角度,系统阐述了人脸检测系统,并将人脸检测方法分为：基于几何特征的方法,基于肤色模型的方法和基于统计理论的方法,并对各个方法的优缺点进行了比较,最后,对人脸检测今后的发展方向进行了探讨。