Arabic writer identification based on hybrid spectral–statistical measures

Many techniques have been reported for handwriting-based writer identification. None of these techniques assume that the written text is in Arabic. In this paper we present a new technique for feature extraction based on hybrid spectral–statistical measures (SSMs) of texture. We show its effectiveness compared with multiple-channel (Gabor) filters and the grey-level co-occurrence matrix (GLCM), which are well-known techniques yielding a high performance in writer identification in Roman handwriting. Texture features were extracted for wide range of frequency and orientation because of the nature of the spread of Arabic handwriting compared with Roman handwriting, and the most discriminant features were selected with a model for feature selection using hybrid support vector machine–genetic algorithm techniques. Four classification techniques were used: linear discriminant classifier (LDC), support vector machine (SVM), weighted Euclidean distance (WED), and the K nearest neighbours (K_NN) classifier. Experiments were performed using Arabic handwriting samples from 20 different people and very promising results of 90.0% correct identification were achieved.     

Ridge regression-based feature extraction for hyperspectral data

Feature extraction based on ridge regression (FERR) is proposed in this article. In FERR, a feature vector is defined in each spectral band using the mean of all classes in that dimension. Then, it is modelled using a linear combination of its farthest neighbours from among other defined feature vectors. The representation coefficients obtained by solving the ridge regression model compose the projection matrix for feature extraction. FERR can extract each desired number of features while the other methods such as linear discriminant analysis (LDA) and generalized discriminant analysis (GDA) have limitations in the number of extracted features. Experimental results on four popular real hyperspectral images show that the efficiency of FERR is superior to those of other supervised feature extraction methods in small sample-size situations. For example, for the Indian Pines dataset, the comparison between the highest average classification accuracies achieved by different feature extraction methods using a support vector machine (SVM) classifier and 16 training samples per class shows that FERR is 7% more accurate than nonparametric weighted feature extraction and is also 9% better than GDA. LDA, having the singularity problem in the small sample-size situations, has 40% less accuracy than FERR. The experiments show that generally the performance of FERR using the SVM classifier is better than when using the maximum likelihood classifier.     

基于优化Gabor滤波器和GMRF的笔迹特征提取方法

提取有效的特征一直是笔迹鉴别的关键问题,针对传统Gabor滤波器特征提取方法存在的不足,充分利用Gabor滤波系数间的相关关系,提出一种融合全局特征和局部特征的特征提取方法。该方法先通过字符笔画的方向梯度直方图（HOG）来优化Gabor滤波器的角度参数,再利用高斯马尔科夫随机场（GMRF）模型对Gabor滤波图像中的不同局部结构信息进行描述,最终得到笔迹图像的整体特征。以楷书四大家的真迹样本和收集的英文手稿作为实验数据,采用最小加权欧式距离分类器对笔迹样本进行分类,通过五重交叉验证法分别得到97.6%和88.3%的正确分类率,表明该方法提取的特征具有较强的笔迹表征能力,是一种有效的笔迹特征提取方法。     

Improving brain tumor characterization on MRI by probabilistic neural networks and non-linear transformation of textural features

The aim of the present study was to design, implement and evaluate a software system for discriminating between metastatic and primary brain tumors (gliomas and meningiomas) on MRI, employing textural features from routinely taken T1 post-contrast images. The proposed classifier is a modified probabilistic neural network (PNN), incorporating a non-linear least squares features transformation (LSFT) into the PNN classifier. Thirty-six textural features were extracted from each one of 67 T1-weighted post-contrast MR images (21 metastases, 19 meningiomas and 27 gliomas). LSFT enhanced the performance of the PNN, achieving classification accuracies of 95.24% for discriminating between metastatic and primary tumors and 93.48% for distinguishing gliomas from meningiomas. To improve the generalization of the proposed classification system, the external cross-validation method was also used, resulting in 71.43% and 81.25% accuracies in distinguishing metastatic from primary tumors and gliomas from meningiomas, respectively. LSFT improved PNN performance, increased class separability and resulted in dimensionality reduction.     

Improving handwriting based gender classification using ensemble classifiers

This paper presents a system to predict gender of individuals from offline handwriting samples. The technique relies on extracting a set of textural features from handwriting samples of male and female writers and training multiple classifiers to learn to discriminate between the two gender classes. The features include local binary patterns (LBP), histogram of oriented gradients (HOG), statistics computed from gray-level co-occurrence matrices (GLCM) and features extracted through segmentation-based fractal texture analysis (SFTA). For classification, we employ artificial neural networks (ANN), support vector machine (SVM), nearest neighbor classifier (NN), decision trees (DT) and random forests (RF). Classifiers are then combined using bagging, voting and stacking techniques to enhance the overall system performance. The realized classification rates are significantly better than those of the state-of-the-art systems on this problem validating the ideas put forward in this study.     

Text legibility and the letter superiority effect

Effects of font design and electronic display parameters upon text legibility were determined using a threshold size method. Participants' visual acuity (inverse of the minimum detection size, representing the threshold legibility for each condition) was measured using upper- and lowercase letters and lowercase words in combinations of 6 fonts, 3 font-smoothing modes, 4 font sizes, 10 pixel heights, and 4 stroke widths. Individual lowercase letters were 10% to 20% more legible than lowercase words (i.e., lowercase words must be 10%-20% larger to have the same threshold legibility). This letter superiority effect suggests that individual letters play a large role and word shape plays a smaller role, if any, in word identification at threshold. Pixel height, font, stroke width, and font smoothing had significant main effects on threshold legibility. Optimal legibility was attained at 9 pixels (10 points). Verdana and Arial were the most legible fonts; Times New Roman and Franklin were least legible. Subpixel rendering (ClearType) improved threshold legibility for some fonts and, in combination with Verdana, was the most legible condition. Increased stroke width (bold) improved threshold legibility but only at the thinnest width tested. Potential applications of this research include optimization of font design for legibility and readability.     

A comparative study of cloud classification techniques

The purpose of this study was to determine the importance of infrared vs. visual features, textural vs. spectral features, hierarchical vs. single-stage decision logic, and quadratic vs. linear discriminant functions for classification of NOAA-1 visible and infrared tropical cloud data. Both a four-class problem, in which cloud types were grouped into (1) “low”, (2) “mix”, (3) “cirrus”, and (4) “cumulonimbus” classes, and a three-class problem, in which the “mix” class was excluded, were analyzed. The addition of at least one visual spectral feature to infrared spectral features improved the ability of the classifier to recognize all cloud classes except “low”. Combining textural features with spectral features did not significantly improve classification results achieved using only spectral features. For the four-class problem, a classification accuracy of 91% was obtained by using a two-stage variation of a single-stage, maximum likelihood classifier. For the three-class problem, classification accuracies of 98% were obtained using either single-stage or hierarchical decision logic and either quadratic or linear discriminant functions.     

Maximum likelihood training of probabilistic neural networks

A maximum likelihood method is presented for training probabilistic neural networks (PNN's) using a Gaussian kernel, or Parzen window. The proposed training algorithm enables general nonlinear discrimination and is a generalization of Fisher's method for linear discrimination. Important features of maximum likelihood training for PNN's are: 1) it economizes the well known Parzen window estimator while preserving feedforward NN architecture, 2) it utilizes class pooling to generalize classes represented by small training sets, 3) it gives smooth discriminant boundaries that often are "piece-wise flat" for statistical robustness, 4) it is very fast computationally compared to backpropagation, and 5) it is numerically stable. The effectiveness of the proposed maximum likelihood training algorithm is assessed using nonparametric statistical methods to define tolerance intervals on PNN classification performance.     

联机手写维吾尔文字母识别方法

通过分析维吾尔文字母自身的结构和书写特点,提出一种联机手写维吾尔文字母识别方案,并选择在手写汉字识别技术中所提出来的归一化、特征提取及常用的分类方法,从中找出最佳的技术选择。在实验对比中,采用8种不同的归一化预处理方法,基于坐标归一化的特征提取 (NCFE) 方法,以及改进的二次分类函数(MQDF)、判别学习型二次判别函数(DLQDF)、学习矢量量化(LVQ)、支持向量机(SVM)4种分类器。同时,再考虑字符在文档中的空间几何特征,进一步提高识别性能。在128个维吾尔文字母类别、38 400个测试样本的实验中,正确识别率最高达89。08%,为进一步研究面向维吾尔文字母特性的识别技术奠定重要基础。     

Gradient feature extraction for classification-based face detection

Face detection from cluttered images is challenging due to the wide variability of face appearances and the complexity of image backgrounds. This paper proposes a classification-based method for locating frontal faces in cluttered images. To improve the detection performance, we extract gradient direction features from local window images as the input of the underlying two-class classifier. The gradient direction representation provides better discrimination ability than the image intensity, and we show that the combination of gradient directionality and intensity outperforms the gradient feature alone. The underlying classifier is a polynomial neural network (PNN) on a reduced feature subspace learned by principal component analysis (PCA). The incorporation of the residual of subspace projection into the PNN was shown to improve the classification performance. The classifier is trained on samples of face and non-face images to discriminate between the two classes. The superior detection performance of the proposed method is justified in experiments on a large number of images.     

WRITER IDENTIFICATION OF ARABIC TEXT USING STATISTICAL AND STRUCTURAL FEATURES

This article addresses writer identification of handwritten Arabic text. Several types of structural and statistical features were extracted from Arabic handwriting text. A novel approach was used to extract structural features that build on some of the main characteristics of the Arabic language. Connected component features for Arabic handwritten text as well as gradient distribution features, windowed gradient distribution features, contour chain code distribution features, and windowed contour chain code distribution features were extracted. A nearest neighbor (NN) classifier was used with the Euclidean distance measure. Data reduction algorithms (viz. principal component analysis [PCA], linear discriminant analysis [LDA], multiple discriminant analysis [MDA], multidimensional scaling [MDS], and forward/backward feature selection algorithm) were used. A database of 500 paragraphs handwritten in Arabic by 250 writers was used. The paragraphs used were randomly generated from a large corpus. NN provided the best accuracy in text-independent writer identification with top-1 result of 88.0%, top-5 result of 96.0%, and top-10 result of 98.5% for the first 100 writers. Extending the work to include all 250 writers and with the backward feature selection algorithm (using 54 out of 83 features), the system attained a top-1 result of 75.0%, top-5 result of 91.8%, and top-10 result of 95.4%.     

A method for classification accuracy evaluation for a precipitation‐oriented classifier

A method of classification accuracy evaluation for a cloud and precipitation classifier applied to geostationary meteorological satellite data is presented. The method has been developed to evaluate the accuracy of a rather precise classification algorithm. The algorithm produces nine classes, four of which involve precipitation. The classes are: (1) clear or insignificant cloud, (2) low thin cloud with no rain, (3) low or middle thin cloud with no rain, (4) low or middle thick cloud with no rain, (5) middle or high cloud with no rain, (6) middle or high cloud with the possibility of rain, (7) middle or high cloud with light–moderate precipitation, (8) middle–high cloud with moderate–heavy precipitation, (9) heavy thunderstorm. The evaluation classifier has been tested for its accuracy (ground truth) using comparison between actual meteorological weather reports and classification results derived from the algorithm applied. For the estimation of classification accuracy, the omission/commission method is applied between the observed and the classification‐produced values. The classifier used has proved to be very reliable for classifying major cloud types and precipitation, tested during the synoptic situation of depression systems approaching the south Balkan Peninsula from the west. In that synoptic situation, different intensities of rainfall as well as heavy thunderstorm were present, and the results are very satisfactory. The method can be used to evaluate classification results produced by algorithms applied to meteorological satellite data, classifying precipitation areas as well as the heaviness of precipitation.     

Using k-nn and discriminant analyses to classify rain forest types in a Landsat TM image over northern Costa Rica

Conservation and land use planning in humid tropical lowland forests urgently need accurate remote sensing techniques to distinguish among floristically different forest types. We investigated the degree to which floristically and structurally defined Costa Rican lowland rain forest types can be accurately discriminated by a non-parametric k nearest neighbors (k-nn) classifier or linear discriminant analysis. Pixel values of Landsat Thematic Mapper (TM) image and Shuttle Radar Topography Mission (SRTM) elevation model extracted from segments or from 5 × 5 pixel windows were employed in the classifications. 104 field plots were classified into three floristic and one structural type of forest (regrowth forest). Three floristically defined forest types were formed through clustering the old-growth forest plots (n = 52) by their species specific importance values. An error assessment of the image classification was conducted via cross-validation and error matrices, and overall percent accuracy and Kappa scores were used as measures of accuracy. Image classification of the four forest types did not adequately distinguish two old-growth forest classes, so they were merged into a single forest class. The resulting three forest classes were most accurately classified by the k-nn classifier using segmented image data (overall accuracy 91%). The second best method, with respect to accuracy, was the k-nn with 5 × 5 pixel windows data (89% accuracy), followed by the canonical discriminant analysis using the 5 × 5 pixel window data (86%) and the segment data (82%). We conclude the k-nn classifier can accurately distinguish floristically and structurally different rain forest types. The classification accuracies were higher for the k-nn classifier than for the canonical discriminant analysis, but the differences in Kappa scores were not statistically significant. The segmentation did not increase classification accuracy in this study.     

基于FCM-PNN分类器的说话人识别

说话人识别的本质就是模式分类。传统分类器算法中参数模型方法的主要缺点是预先假定的概率分布函数形式不一定符合待分类的数据。非参数模型方法,如PNN分类器,可以有效地克服参数模型的缺点,但其巨大的内存开销与低的分类速度使得PNN作为大量和高维的数据样本分类几乎不可行。FCM虽具有良好的模糊聚类能力,但无法直接给出概率分类结果。该文提出的FCM-PNN分类器,在FCM聚类的基础上,以贝叶斯置信度为基础,利用PNN进行概率分类。它结合了FCM聚类和PNN概率分类的优势,同时克服了传统参数模型分类和FCM聚类的局限性。实验结果证实了FCM-PNN分类器具有分类精度高、速度快及揭示细节的能力。     

Soft computing system for bank performance prediction

This paper presents a soft computing based bank performance prediction system. It is an ensemble system whose constituent models are a multi-layered feed forward neural network trained with backpropagation (MLFF-BP), a probabilistic neural network (PNN) and a radial basis function neural network (RBFN), support vector machine (SVM), classification and regression trees (CART) and a fuzzy rule based classifier. Further, principal component analysis (PCA) based hybrid neural networks, viz. PCA-MLFF-BP, PCA-PNN and PCA-RBF are also included as constituents of the ensemble. Moreover, GRNN and PNN were trained with a genetic algorithm to optimize the smoothing factors. Two ensembles (i) simple majority voting based and (ii) weightage based are implemented. This system predicts the performance of a bank in the coming financial year based on its previous 2-years’ financial data. Ten-fold cross-validation is performed in the training sessions and results are validated with an independent production set. It is demonstrated that the ensemble is able to yield lower Type I and Type II errors compared to its constituent models. Further, the ensemble also outperformed an earlier study [P.G. Swicegood, Predicting poor bank profitability: a comparison of neural network, discriminant analysis and professional human judgement, Ph.D. Thesis, Department of Finance, Florida State University, 1998] that used multivariate discriminant analysis (MDA), MLFF-BP and human judgment.     

Predicting the big five personality traits from hand-written text features through semi-supervised learning

Handwriting analysis is a systematic study of preserved graphic structures. Which are generated in the human brain and produced on paper in cursive or printed style. The style in which a text is written reflects an array of meta-information. Personality is a combination of an individual’s behavior, emotion, motivation, and thought-pattern characteristics. It has an impact on one’s life choices, well-being, health, and numerous other preferences. This study investigates the correlation between handwriting features and personality characteristics. The prediction of personality through handwriting analysis needs to investigate the style and structure of writing. This study extracts eleven features from handwriting samples using a graph-based writing representation approach. The Big Five model of personality traits is utilized to find the personality of the writer. To improve classification accuracy utilizes a Semi-supervised Generative Adversarial Network (SGAN). This network uses a small amount of labeled data and a larger amount of unlabeled data to train the classifier. The discriminator works as a multi-class classifier and is trained on labeled, unlabeled, and generator created data. The proposed system predicts 91.3% correct personality results by utilizing the writing features of 173 participants.