基于自组织动态神经网络的图像分割

图像分割是图像处理和模式识别的重要课题,而图像特征空间聚类是图像分割的一种重要方法,认为图像的特征是图像中待分割物体表面所特有而且恒定的特征,并将图像的特征映射到某种几何空间,称为特征空间,并且假定图像中不同的待分割物体在该特征空间中呈现为不同的聚集,提出了自组织动态网络(SODNN)聚类算法,并且利用该算法对图像特征空间聚类.该算法实现了神经网络结构的快速生长和动态调节,具有自动适应数据内在分布特征和聚类结果更为准确稳定的特点.利用SODNN算法对图像颜色空间进行聚类的同时综合了图像的位置信息来实现图像分割.实验表明分割结果与人工分割结果具有较好的一致性.     

基于图层分割的文档图像压缩方法

传统的图像压缩技术，大都基于图像空域和色度空间同质性的假定，在文档图像的压缩中并不能取得最好的压缩效果。针对文档图像的特点，提出了一种基于图层分割的文档图像压缩方法。该方法首先利用多尺度的2色聚类算法进行文档图像的图层分割，然后根据不同图层的特征，分别采用效果最佳的压缩技术，能够获得比传统的方法更好的压缩效果。     

基于两级阈值的图像分割技术在文档图像中的应用

研究图像二值化分割问题。针对模糊或者蜕化文档图像背景与文字融合在一起导致难以区分的难点,提出一种快速有效的两级结构图像分割算法。首先利用迭代算法对图像进行单一阈值分割,在每次迭代过程中以图像均值为依据,对图像进行均衡化处理;在基于全局分割的基础上,在局部范围内根据噪声的统计特性对文档图像进行去噪处理。方法简单高效,实验结果显示该方法能快速地将文档中的文字与背景进行分离,为后续的文档自动化处理提供准确有效的二值化图像。利用该方法,可以方便地拓展到其他类型的二值化处理系统中,例如车牌分割等。     

基于粗糙集理论的图像分割智能决策方法

尽管如今已有多种图像分割算法,但是没有任何一种分割方法能够适用于所有的图像.为了使图像跟踪系统能根据图像特征自适应选取分割算法,给出了一种基于粗糙集理论的图像分割智能决策方法.该方法首先选取若干具代表性的分割算法构成算法库,并用它们对各种样本图像进行分割;然后利用从样本图像中提取出来的各种数值特征,并根据图像分割质量评价标准评判出各样本图像的最优分割算法,用其构成决策信息表;最后应用粗糙集理论来对决策信息表进行离散化处理和属性约简,以生成图像分割算法选取的决策规则.该决策方法解决了图像跟踪系统中分割算法选取的一系列难题.实验证明,该决策方法能比较有效地根据系统所处理图像的特征选取出算法库中最优的分割算法,并可满足车载图像跟踪系统的实时性要求.     

基于纹理谱描述子的文档图像检索算法

新算法首先根据文档图像的特点分割图像文本区域,并将文档图像中字符的边缘信息使用纹理谱进行描述,计算纹理谱图像的直方图。相对于直接使用灰度直方图进行图像检索,该算法具有更好的区分度。实验结果表明,该方法具有很高的查准率,并对剪切、旋转操作表现出很好的稳定性,适合文档图像检索。     

基于精度依据准则的图像分割算法评价

在图像处理中,图像分割是一类重要的研究方向。图像分割算法的好坏,影响到分割结果的优劣,因此对分割算法的性能评估十分重要。本文提出了一种图像分割算法性能的评价方法——精度依据准则,该准则是对原始特征量值和实际特征量值做比较,通过对绝对值的大小来判断算法的好坏。通过实验比较,该方法具有不错的算法性能评估准确度。     

基于字符规范化的文档图像水印算法

运用字符规范化和小波变换的知识,提出一种将文档图像分割成字符图像,再对字符图像规范化,然后将随机序列嵌入到小波图像低频系数的水印算法.根据视觉系统纹理掩蔽特性,将不同强度的水印分量嵌入到了不同的小波系数中.由于文档图像分割和规范化本身具有抗几何攻击的特性,故该方法对缩放、小角度旋转有一定的鲁棒性,实验结果表明:该方法在文档图像上比其它方法更具备优越性.     

综合文字和非文字区域特征的文档图像检索

提出一种改进的自适应文字区域提取算法,将文档图像分割成文字区域和非文字区域。对文字区域提取连通字符间空白、连通字符高度和宽度等局部特征,以及书写样式、段落特征等全局特征;对非文字区域,提取关键块特征。然后利用检索算法将文字区域特征和非文字区域特征结合起来,提高检索的准确性。同时,在检索算法中引入多维数据检索结构,有效地提高检索速度。通过对大规模文档数据库（包含12 024个文档）的检索,表明该算法具有较高的效率,优于现有的一般文档图像检索算法。     

基于相位一致性的眼底图像视网膜血管分割

眼底图像的视网膜血管分割是眼底图像处理的重要组成部分,视网膜血管对于医学研究和临床诊断有着重要的作用。传统图像分割算法都有一定的缺陷,而相位一致性算法由于不受对亮度和对比度的影响,且有着较好的分割效果,可以用于图像特征的提取和分割。为此提出了将相位一致性算法应用于眼底图像的血管提取中,采用真实的眼底图像数据库进行实践,证明了可较好地用于眼底图像视网膜血管分割。     

基于链式竞争遗传算法的KSW熵的图像分割

针对最佳熵阈值图像分割算法过程中计算复杂度高的问题,提出了一种基于链式竞争遗传算法的最佳熵阈值确定法(KSW熵法)的图像分割算法.通过将3个邻域的链式竞争引入到常规遗传算法框架下,实现特征选择过程;将改进的遗传算法应用到最佳阈值图像分割算法中,完成对阈值的寻优过程.仿真实验结果与分析表明:算法在分割速度和效果上均优于传统的最佳阈值图像分割算法和单纯的遗传优化最佳阈值图像分割算法.     

快速成型切片数据的优化算法研究

为了能够顺利地进行 STL模型切片轮廓数据的进一步处理 ,提出了对切片数据进行优化处理的算法 .对由于STL模型的缺陷造成切片之后的轮廓信息数据有大量的冗余数据 ,提出了一种冗余数据的滤除算法 ;针对切片轮廓的不封闭 ,给出了有效的修正算法 ;同时给出了对切片轮廓的内外边界进行自动识别的算法 .该算法高效简单 ,提高了后续的数据处理的效率和成型件的加工质量 ,改善了零件成型的加工性能     

A survey of document image classification: problem statement,classifier architecture and performance evaluation

Document image classification is an important step in Office Automation, Digital Libraries, and other document image analysis applications. There is great diversity in document image classifiers: they differ in the problems they solve, in the use of training data to construct class models, and in the choice of document features and classification algorithms. We survey this diverse literature using three components: the problem statement, the classifier architecture, and performance evaluation. This brings to light important issues in designing a document classifier, including the definition of document classes, the choice of document features and feature representation, and the choice of classification algorithm and learning mechanism. We emphasize techniques that classify single-page typeset document images without using OCR results. Developing a general, adaptable, high-performance classifier is challenging due to the great variety of documents, the diverse criteria used to define document classes, and the ambiguity that arises due to ill-defined or fuzzy document classes.     

K最近邻算法理论与应用综述

k最近邻算法（kNN）是一个十分简单的分类算法,该算法包括两个步骤：（1）在给定的搜索训练集上按一定距离度量,寻找一个k的值。（2）在这个kNN算法当中,根据大多数分为一致的类来进行分类。kNN算法具有的非参数性质使其非常易于实现,并且它的分类误差受到贝叶斯误差的两倍的限制,因此,kNN算法仍然是模式分类的最受欢迎的选择。通过总结多篇使用了基于kNN算法的文献,详细阐述了每篇文献所使用的改进方法,并对其实验结果进行了分析;通过分析kNN算法在人脸识别、文字识别、医学图像处理等应用中取得的良好分类效果,对kNN算法的发展前景无比期待。     

Learning extremely shared middle-level image representation for scene classification

Learning middle-level image representations is very important for the computer vision community, especially for scene classification tasks. Middle-level image representations currently available are not sparse enough to make training and testing times compatible with the increasing number of classes that users want to recognize. In this work, we propose a middle-level image representation based on the pattern that extremely shared among different classes to reduce both training and test time. The proposed learning algorithm first finds some class-specified patterns and then utilizes the lasso regularization to select the most discriminative patterns shared among different classes. The experimental results on some widely used scene classification benchmarks (15 Scenes, MIT-indoor 67, SUN 397) show that the fewest patterns are necessary to achieve very remarkable performance with reduced computation time.     

Segmentation of document images

Several methods for segmentation of document images (maps, drawings, etc.) are explored. The segmentation operation is posed as a statistical classification task with two pattern classes: print and background. A number of classification strategies are available. All require some prior information about the distribution of gray levels for the two classes. Training (either supervised or unsupervised) is employed to form these initial density estimates. Automatic updating of the class-conditional densities is performed within subregions in the image to adapt these global density estimates to the local image area. After local class-conditional densities have been obtained, each pixel is classified within the window using several techniques: a noncontextual Bayes classifier, Besag's classifier, relaxation, Owen and Switzer's classifier, and Haslett's classifier. Four test images were processed. In two of these, the relaxation method performed best, and in the other two, the noncontextual method performed best. Automatic updating improved the results for both classifiers     

Vector projection for face recognition

In this paper, a novel approach for face recognition is proposed by using vector projection length to formulate the pattern recognition problem. Face images of a single-object class are more similar than those of different-object classes. The projection length of a test image vector on the direction of a training image vector can measure the similarity of the two images. But the decision cannot be made by only a training image which is the most similar to the test one, the mean image vector of each class also contributes to the final classification. Thus, the decision of the proposed vector projection classification (VPC) algorithm is ruled in favor of the maximum combination projection length. To address the partial occlusion problem in face recognition, we propose a local vector projection classification (LVPC) algorithm. The experimental results show that the proposed VPC and LVPC approaches are efficient and outperform some existing approaches.     

Class-dependent projection based method for text categorization

Text categorization presents unique challenges to traditional classification methods due to the large number of features inherent in the datasets from real-world applications of text categorization, and a great deal of training samples. In high-dimensional document data, the classes are typically categorized only by subsets of features, which are typically different for the classes of different topics. This paper presents a simple but effective classifier for text categorization using class-dependent projection based method. By projecting onto a set of individual subspaces, the samples belonging to different document classes are separated such that they are easily to be classified. This is achieved by developing a new supervised feature weighting algorithm to learn the optimized subspaces for all the document classes. The experiments carried out on common benchmarking corpuses showed that the proposed method achieved both higher classification accuracy and lower computational costs than some distinguishing classifiers in text categorization, especially for datasets including document categories with overlapping topics.     

A deep stacked wavelet auto-encoders to supervised feature extraction to pattern classification

The major issue in pattern classification is in the extraction of features in the training phase. The focus of this work is on combining the ability of wavelet networks and the deep learning techniques to propose a new supervised feature extraction method to pattern classification. This new approach allows the classification of all classes of the dataset by the reconstruction of a Deep Stacked wavelet Auto-Encoder. This Network is obtained after a series of wavelet Auto-Encoders followed by a Softmax classifier at the last layer. Finally, a fine-tuning is applied for the improvement of our result using a back propagation algorithm. Our approach is tested with different image datasets which are the COIL-100, the APTI and the ImageNet datasets and is also tested with two other audio corpuses that contain Arabic words and French words. The experimental test demonstrates the efficiency of our network for image and audio classification compared to other methods.     

基于类别方差的特征权重算法

特征权重计算是文本分类过程的基础,传统基于概率的特征权重算法,往往只对词频,逆文档频和逆类频等进行统计,忽略了类别之间的相互关系。而对于多分类问题,类别之间的关系对统计又有重要意义。因此,针对这一不足,本文提出了基于类别方差的特征权重算法,通过计算类别文档频率的方差来度量类别之间的联系,并在搜狗新闻数据集上对五种特征权重算法进行分类实验。结果表明,与其他四种特征权重算法相比,本文提出的算法在F1宏平均和F1微平均上都有较大的提高,提升了文本分类的效果。