Eigen-deformations for elastic matching based handwritten character recognition

Deformations in handwritten characters have category-dependent tendencies. In this paper, the estimation and the utilization of such tendencies called eigen-deformations are investigated for the better performance of elastic matching based handwritten character recognition. The eigen-deformations are estimated by the principal component analysis of actual deformations automatically collected by the elastic matching. From experimental results it was shown that typical deformations of each category can be extracted as the eigen-deformations. It was also shown that the recognition performance can be improved significantly by using the eigen-deformations for the detection of overfitting, which is the main cause of the misrecognition in the elastic matching based recognition methods.     

An MLP-orthogonal Gaussian mixture model hybrid model for Chinese bank check printed numeral recognition

A hybrid model based on the combination of an orthogonal Gaussian mixture model (OGMM) and a multilayer perceptron (MLP) is proposed in this paper that is to be used for Chinese bank check machine printed numeral recognition. The combination of MLP with OGMM produces a hybrid model with high recognition accuracy as well as an excellent outlier rejection ability. Experimental results show that the proposed model can satisfy the requirements of Chinese bank check printed numeral recognition where high recognition accuracy, high processing speed, and high reliability are needed. Correspondence to: Hui Zhu     

Regularized discriminant analysis for face recognition

This paper studies regularized discriminant analysis (RDA) in the context of face recognition. We check RDA sensitivity to different photometric preprocessing methods and compare its performance to other classifiers. Our study shows that RDA is better able to extract the relevant discriminatory information from training data than the other classifiers tested, thus obtaining a lower error rate. Moreover, RDA is robust under various lighting conditions while the other classifiers perform badly when no photometric method is applied.     

Multiresolution recognition of unconstrained handwritten numerals with wavelet transform and multilayer cluster neural network

In this paper, we propose a new scheme for multiresolution recognition of unconstrained handwritten numerals using wavelet transform and a simple multilayer cluster neural network. The proposed scheme consists of two stages: a feature extraction stage for extracting multiresolution features with wavelet transform, and a classification stage for classifying unconstrained handwritten numerals with a simple multilayer cluster neural network. In order to verify the performance of the proposed scheme, experiments with unconstrained handwritten numeral database of Concordia University of Canada, Electro-Technical Laboratory of Japan, and Electronics and Telecommunications Research Institute of Korea were performed. The error rates were 3.20%, 0.83%, and 0.75%, respectively. These results showed that the proposed scheme is very robust in terms of various writing styles and sizes.     

基于模版对比的手写体数字识别神经网络模型

针对现有手写体数字识别神经网络模型的不足,提出基于模版对比的改进方法。建立8×12像素的手写体数字0～9的标准模版,则模版中每个数字与其他数字之间存在一定的像素差异,以此作为标准模版差异值。由于书写存在不确定性,采用在一定范围内随机增大或减小标准模版差异值的方法来构建神经网络模型的训练样本、检验样本与测试样本。在遵循建模基本原则和步骤的情况下,建立了泛化能力较好的手写体数字识别的神经网络模型。实验表明：该方法建模便捷、实用性好,测试样本的正确识别率达99.6%以上。     

基于2DPCA和RBF神经网络的人脸识别方法

采用2DPCA方法提取人脸图像的特征值,通过RBF神经网络进行训练和识别,提出一种基于2DPCA和RBF神经网络的人脸识别方法,并将此方法应用于ORL人脸库。实验结果表明,该方法不仅具有较好的人脸图像识别能力,而且能明显缩短识别算法的运行时间。     

Performance evaluation of pattern classifiers for handwritten character recognition

This paper describes a performance evaluation study in which some efficient classifiers are tested in handwritten digit recognition. The evaluated classifiers include a statistical classifier (modified quadratic discriminant function, MQDF), three neural classifiers, and an LVQ (learning vector quantization) classifier. They are efficient in that high accuracies can be achieved at moderate memory space and computation cost. The performance is measured in terms of classification accuracy, sensitivity to training sample size, ambiguity rejection, and outlier resistance. The outlier resistance of neural classifiers is enhanced by training with synthesized outlier data. The classifiers are tested on a large data set extracted from NIST SD19. As results, the test accuracies of the evaluated classifiers are comparable to or higher than those of the nearest neighbor (1-NN) rule and regularized discriminant analysis (RDA). It is shown that neural classifiers are more susceptible to small sample size than MQDF, although they yield higher accuracies on large sample size. As a neural classifier, the polynomial classifier (PC) gives the highest accuracy and performs best in ambiguity rejection. On the other hand, MQDF is superior in outlier rejection even though it is not trained with outlier data. The results indicate that pattern classifiers have complementary advantages and they should be appropriately combined to achieve higher performance. Received: July 18, 2001 / Accepted: September 28, 2001     

Neural network language models for off-line handwriting recognition

Unconstrained off-line continuous handwritten text recognition is a very challenging task which has been recently addressed by different promising techniques. This work presents our latest contribution to this task, integrating neural network language models in the decoding process of three state-of-the-art systems: one based on bidirectional recurrent neural networks, another based on hybrid hidden Markov models and, finally, a combination of both. Experimental results obtained on the IAM off-line database demonstrate that consistent word error rate reductions can be achieved with neural network language models when compared with statistical N-gram language models on the three tested systems. The best word error rate, 16.1%, reported with ROVER combination of systems using neural network language models significantly outperforms current benchmark results for the IAM database.     

(2D)LDA: An efficient approach for face recognition

Although 2DLDA algorithm obtains higher recognition accuracy, a vital unresolved problem of 2DLDA is that it needs huge feature matrix for the task of face recognition. To overcome this problem, this paper presents an efficient approach for face image feature extraction, namely, (2D)²LDA method. Experimental results on ORL and Yale database show that the proposed method obtains good recognition accuracy despite having less number of coefficients.     

Face recognition with one training image per person

At present there are many methods that could deal well with frontal view face recognition. However, most of them cannot work well when there is only one training image per person. In this paper, an extension of the eigenface technique, i.e. projection-combined principal component analysis, (PC)²A, is proposed. (PC)²A combines the original face image with its horizontal and vertical projections and then performs principal component analysis on the enriched version of the image. It requires less computational cost than the standard eigenface technique and experimental results show that on a gray-level frontal view face database where each person has only one training image, (PC)²A achieves 3–5% higher accuracy than the standard eigenface technique through using 10–15% fewer eigenfaces.     

基于SOC网络的商业银行信用风险识别模型

针对自组织竞争(SOC)神经网络在解决模式分类问题上的优势,结合主成分分析法来构建商业银行信用风险识别模型.首先构造一套用于描述贷款企业信用状况的指标体系,然后使用主成分分析法提取特征指标,再采用SOC神经网络进行非监督分类.通过选取陕西省2007年度在沪、深两市交易的26家上市公司作为样本进行实证分析,实证结果表明:模型对信用风险具有较强的识别能力,同时对商业银行还有较好的预测功能.     

Maximum mutual information training for an online neural predictive handwritten word recognition system

In this paper, we present a hybrid online handwriting recognition system based on hidden Markov models (HMMs). It is devoted to word recognition using large vocabularies. An adaptive segmentation of words into letters is integrated with recognition, and is at the heart of the training phase. A word-model is a left-right HMM in which each state is a predictive multilayer perceptron that performs local regression on the drawing (i.e., the written word) relying on a context of observations. A discriminative training paradigm related to maximum mutual information is used, and its potential is shown on a database of 9,781 words. Received June 19, 2000 / Revised October 16, 2000     

A modular clutter rejection technique for FLIR imagery using region-based principal component analysis

A modular clutter-rejection technique that uses region-based principal component analysis (PCA) is proposed. A major problem in FLIR ATR is the poorly centered targets generated by the preprocessing stage. Our modular clutter-rejection system usesstatic as well as dynamic region of interest (ROI) extraction to overcome the problem of poorly centered targets. In static ROI extraction, the center of the representative ROI coincides with the center of the potential target image. In dynamic ROI extraction, a representative ROI is moved in several directions with respect to the center of the potential target image to extract a number of ROIs. Each module in the proposed system applies region-based PCA to generate the feature vectors, which are subsequently used to make a decision about the identity of the potential target. Region-based PCA uses topological features of the targets to reject false alarms. In this technique, a potential target is divided into several regions and a PCA is performed on each region to extract regional feature vectors. We propose using regional feature vectors of arbitrary shapes and dimensions that are optimized for the topology of a target in a particular region. These regional feature vectors are then used by a two-class classifier based on the learning vector quantization to decide whether a potential target is a false alarm or a real target. We also present experimental results using real-life data to evaluate and compare the performance of the clutter-rejection systems with static and dynamic ROI extraction.     

Eigenspace updating for non-stationary process and its application to face recognition

In this paper, we introduce a novel approach to modeling non-stationary random processes. Given a set of training samples sequentially, we can iteratively update the eigenspace to manifest the current statistics provided by each new sample. The updated eigenspace is derived based more on recent samples and less on older samples, controlled by a number of decay parameters. Extensive study has been performed on how to choose these decay parameters. Other existing eigenspace updating algorithms can be regarded as special cases of our algorithm. We show the effectiveness of the proposed algorithm with both synthetic data and practical applications on face recognition. Significant improvements have been observed on face images with different variations, such as pose, expression and illumination variations. We expect the proposed algorithm to have other applications in active recognition and modeling as well.     

一种全局收敛的PCA神经网络学习算法

主元分析(PCA)也称为K-L变换是进行特征提取的一种重要方法。近年来,为了处理海量数据,许多基于Hebbian学习算法的PCA神经网络被提出来。传统的算法,通常不能保证其收敛性或者收敛速度较慢。基于CRLS神经网络,本文提出了一种新的确保权向量收敛的学习算法,本算法无须在计算中规格化权向量。同时也证明了该学习算法使得权向量收敛到最大特征值所对应的特征向量。实验表明,与传统的CRLS神经网络比较,本文算法准确性得到极大提高。     

Neural network analysis of ophthalmic arterial doppler signals with Uveitis disease

Doppler ultrasound is known as a reliable technique, which demonstrates the flow characteristics and resistance of ophthalmic arteries. In this study, ophthalmic arterial Doppler signals were obtained from 95 subjects—that 45 of them had suffered from Uveitis disease and the rest of them had been healthy subjects. Multilayer perceptron neural network (MLPNN) employing quick propagation training algorithm was used to detect the presence of Uveitis disease. Spectral analysis of ophthalmic arterial Doppler signals was performed by autoregressive moving average (ARMA) method for determining the MLPNN inputs. The MLPNN was trained with training set, cross validated with cross validation set and tested with testing set. All these data sets were obtained from ophthalmic arteries of healthy subjects and subjects suffering from Uveitis disease. Performance indicators and statistical measures were used for evaluating the MLPNN. The correct classification rate was 95.83% for healthy subjects and 91.30% for subjects suffering from Uveitis disease. Based on the accuracy of the MLPNN detections, it can be mentioned that the classification of ophthalmic arterial Doppler signals with Uveitis disease is feasible by the MLPNN employing quick propagation training algorithm.     

Diagonal principal component analysis for face recognition

In this paper, a novel subspace method called diagonal principal component analysis (DiaPCA) is proposed for face recognition. In contrast to standard PCA, DiaPCA directly seeks the optimal projective vectors from diagonal face images without image-to-vector transformation. While in contrast to 2DPCA, DiaPCA reserves the correlations between variations of rows and those of columns of images. Experiments show that DiaPCA is much more accurate than both PCA and 2DPCA. Furthermore, it is shown that the accuracy can be further improved by combining DiaPCA with 2DPCA.     

基于BP神经网络的主分量分析人脸识别算法

提出了基于BP神经网络的主分量人脸识别算法。该算法首先用小波变换对人脸图像进行小波分解,形成低频小波子图,然后用主分量分析法构造特征脸子空间,将人脸图像在特征空间的投影作为BP神经网络的输入,由BP神经网络和后验概率转换器构成人脸识别器。针对ORL人脸库的实验结果表明该方法具有较高的识别率。     

Sensitivity analysis of artificial neural networks for just-suspension speed prediction in solid-liquid mixing systems: Performance comparison of MLPNN and RBFNN

Just-suspension speed (Njs) is an important parameter for stirred tank design using a solid-liquid mixing system in the chemical process industry. However, current correlations for Njs suffer from uncertainty from limited experimental databases and limitations due to many parameters that play an important role in Njs determination. A comprehensive computation of the radial basis function neural network (RBFNN) was developed based on solid-liquid mixing experiments, which contain 935 datasets for the prediction of Njs. The Njs values were obtained experimentally using Zwietering correlation with different solid loading percentages, solid particle density, solid particle diameter, mixing solvent density, number of impeller blades, impeller diameter, impeller blade hub angle, impeller blade tip angle, the width of the impeller blade and the ratio of the clearance between the impeller and the bottom of the tank with the tank diameter. The RBFNN proved to have a much better ability to accurately predict the desired Njs compared to MLPNN even after decreasing the number of input variables from 11 to 8. Thus, the computational RBFNN model results will be useful for extending the application of a solid-liquid mixing system for estimating the just-suspension speed for stirred tank design.     

Face recognition using the embedded HMM with second-order block-specific observations

The paper is concerned with face recognition using the embedded hidden Markov model (EHMM) with second-order block-specific observations. The proposed method partitions a face image into a 2-D lattice type, composed of many blocks. Each block is represented by the second-order block-specific observation that consists of a combination of first- and second-order feature vectors. The first-order (or second-order) feature vector is obtained by projecting the original (or residual) block image onto the first (or second) basis vector that is obtained block-specifically by applying the PCA to a set of original (or residual) block images. A sequence of feature vectors obtained from the top-to-bottom and the left-to-right scanned blocks are used as an observation sequence to train EHMM. The EHMM models the face image in a hierarchical manner as follows. Several super states are used to model the vertical facial features such as the forehead, eyes, nose, mouth, and chin, and several states in the super state are used to model the localized features in a vertical face feature. Recognition is performed by identifying the person of the model that provides the highest value of observation probability. Experimental results show that the proposed recognition method outperforms many existing methods, such as the second-order eigenface method, the EHMM with DCT observations, and the second-order eigenface method using a confidence factor in terms of average of the normalized modified retrieval rank and false identification rate.