Farsi/Arabic handwritten digit recognition based on ensemble of SVD classifiers and reliable multi-phase PSO combination rule

The problem of handwritten digit recognition has long been an open problem in the field of pattern classification and of great importance in industry. The heart of the problem lies within the ability to design an efficient algorithm that can recognize digits written and submitted by users via a tablet, scanner, and other digital devices. From an engineering point of view, it is desirable to achieve a good performance within limited resources. To this end, we have developed a new approach for handwritten digit recognition that uses a small number of patterns for training phase. To improve the overall performance achieved in classification task, the literature suggests combining the decision of multiple classifiers rather than using the output of the best classifier in the ensemble; so, in this new approach, an ensemble of classifiers is used for the recognition of handwritten digit. The classifiers used in proposed system are based on singular value decomposition (SVD) algorithm. The experimental results and the literature show that the SVD algorithm is suitable for solving sparse matrices such as handwritten digit. The decisions obtained by SVD classifiers are combined by a novel proposed combination rule which we named reliable multi-phase particle swarm optimization. We call the method “Reliable” because we have introduced a novel reliability parameter which is applied to tackle the problem of PSO being trapped in local minima. In comparison with previous methods, one of the significant advantages of the proposed method is that it is not sensitive to the size of training set. Unlike other methods, the proposed method uses just 15 % of the dataset as a training set, while other methods usually use (60–75) % of the whole dataset as the training set. To evaluate the proposed method, we tested our algorithm on Farsi/Arabic handwritten digit dataset. What makes the recognition of the handwritten Farsi/Arabic digits more challenging is that some of the digits can be legally written in different shapes. Therefore, 6000 hard samples (600 samples per class) are chosen by K-nearest neighbor algorithm from the HODA dataset which is a standard Farsi/Arabic digit dataset. Experimental results have shown that the proposed method is fast, accurate, and robust against the local minima of PSO. Finally, the proposed method is compared with state of the art methods and some ensemble classifier based on MLP, RBF, and ANFIS with various combination rules.     

A new benchmark on the recognition of handwritten Bangla and Farsi numeral characters

The recognition of Indian and Arabic handwriting is drawing increasing attention in recent years. To test the promise of existing handwritten numeral recognition methods and provide new benchmarks for future research, this paper presents some results of handwritten Bangla and Farsi numeral recognition on binary and gray-scale images. For recognition on gray-scale images, we propose a process with proper image pre-processing and feature extraction. In experiments on three databases, ISI Bangla numerals, CENPARMI Farsi numerals, and IFHCDB Farsi numerals, we have achieved very high accuracies using various recognition methods. The highest test accuracies on the three databases are 99.40%, 99.16%, and 99.73%, respectively. We justified the benefit of recognition on gray-scale images against binary images, compared some implementation choices of gradient direction feature extraction, some advanced normalization and classification methods.     

Invariance analysis of modified C2 features: case study—handwritten digit recognition

Humans are very efficient in recognizing alphanumeric characters, even in the presence of significant image distortions. Recent advances in visual neuroscience have led to a solid model of object and shape recognition in the visual ventral stream which competes with the state-of-the-art computer vision systems on some standard recognition tasks. A modification of this model is also proposed by adding more biologically inspired properties such as sparsification of features, lateral inhibition and feature localization to enhance its performance. In this study, we show that using features proposed by the modified model results in higher handwritten digit recognition rates compared with the original model over English and Farsi handwritten digit datasets. Our analyses also demonstrate higher invariance of the modified model to various image distortions.     

Arabic handwritten digit recognition

In this paper, we fill a gap in the literature by studying the problem of Arabic handwritten digit recognition. The performances of different classification and feature extraction techniques on recognizing Arabic digits are going to be reported to serve as a benchmark for future work on the problem. The performance of well known classifiers and feature extraction techniques will be reported in addition to a novel feature extraction technique we present in this paper that gives a high accuracy and competes with the state-of-the-art techniques. A total of 54 different classifier/features combinations will be evaluated on Arabic digits in terms of accuracy and classification time. The results are analyzed and the problem of the digit ‘0’ is identified with a proposed method to solve it. Moreover, we propose a strategy to select and design an optimal two-stage system out of our study and, hence, we suggest a fast two-stage classification system for Arabic digits which achieves as high accuracy as the highest classifier/features combination but with much less recognition time.     

Generalized K-L transform based combined feature extraction

In this paper, we combine two kinds of features together by virtue of complex vectors and then use the developed generalized K-L transform (or expansion) for feature extraction. The experiments on NUST603 handwritten Chinese character database and CENPARMI handwritten digit database indicate that the proposed method can improve the recognition rate significantly.     

Recognition of Handwritten Arabic Characters using Histograms of Oriented Gradient (HOG)

Optical Character Recognition (OCR) is the process of recognizing printed or handwritten text on paper documents. This paper proposes an OCR system for Arabic characters. In addition to the preprocessing phase, the proposed recognition system consists mainly of three phases. In the first phase, we employ word segmentation to extract characters. In the second phase, Histograms of Oriented Gradient (HOG) are used for feature extraction. The final phase employs Support Vector Machine (SVM) for classifying characters. We have applied the proposed method for the recognition of Jordanian city, town, and village names as a case study, in addition to many other words that offers the characters shapes that are not covered with Jordan cites. The set has carefully been selected to include every Arabic character in its all four forms. To this end, we have built our own dataset consisting of more than 43.000 handwritten Arabic words (30000 used in the training stage and 13000 used in the testing stage). Experimental results showed a great success of our recognition method compared to the state of the art techniques, where we could achieve very high recognition rates exceeding 99%.     

基于并行特征组合与广义K-L变换的字符识别

针对传统的串行特征融合方法的弱点,提出了一种新的并行特征融合方法.该方法的基本思路是:首先,利用复向量将样本空间上的两组特征集组合起来,构成复特征向量空间;然后,从理论上推广了经典的K-L变换方法与3种基本的K-L展开方法,使其适用于复特征向量空间内的特征抽取.此外,还揭示了并行特征融合的对称性质,并详细讨论了并行特征组合的策略问题.最后,用所提出的方法来解决手写体字符的特征抽取与识别问题.在南京理工大学NUST603HW手写体汉字库以及Concordia大学的CENPARMI手写体阿拉伯数字数据库上的实验结果表明,所提出的特征融合方法不仅较大幅度地提高了识别率,而且识别结果优于传统的串行特征融合方法.     

Recognizing handwritten Arabic words using grapheme segmentation and recurrent neural networks

The Arabic alphabet is used in around 27 languages, including Arabic, Persian, Kurdish, Urdu, and Jawi. Many researchers have developed systems for recognizing cursive handwritten Arabic words, using both holistic and segmentation-based approaches. This paper introduces a system that achieves high accuracy using efficient segmentation, feature extraction, and recurrent neural network (RNN). We describe a robust rule-based segmentation algorithm that uses special feature points identified in the word skeleton to segment the cursive words into graphemes. We show that careful selection from a wide range of features extracted during and after the segmentation stage produces a feature set that significantly reduces the label error. We demonstrate that using same RNN recognition engine, the segmentation approach with efficient feature extraction gives better results than a holistic approach that extracts features from raw pixels. We evaluated this segmentation approach against an improved version of the holistic system MDLSTM that won the ICDAR 2009 Arabic handwritten word recognition competition. On the IfN/ENIT database of handwritten Arabic words, the segmentation approach reduces the average label error by 18.5 %, the sequence error by 22.3 %, and the execution time by 31 %, relative to MDLSTM. This approach also has the best published accuracies on two IfN/ENIT test sets.     

基于PCA初始化卷积核的CNN手写数字识别算法

针对卷积神经网络对手写数字识别训练在卷积核随机初始化情况下收敛速度慢和识别率低的问题，提出一种主成分分析（PCA）初始化卷积核的卷积神经网络（CNN）手写数字识别算法。算法首先选取训练样本集并将其送入CNN，在相应层对Feature Map进行全覆盖取图像块处理，然后进行分层PCA学习，将学习到的特征向量做为对应卷积层的卷积核参数进行初始化，最后再用这些卷积核对原始图像进行卷积操作。实验结果表明，与随机初始化卷积核的CNN手写数字识别算法相比，改进的算法在应用MNIST数据库训练时不仅收敛，而且在产生相同均方误差的情况下迭代次数少，识别率高。     

Feature representation selection based on Classifier Projection Space and Oracle analysis

One of the main problems in pattern recognition is obtaining the best set of features to represent the data. In recent years, several feature extraction algorithms have been proposed. However, due to the high degree of variability of the patterns, it is difficult to design a single representation that can capture the complex structure of the data. One possible solution to this problem is to use a multiple-classifier system (MCS) based on multiple feature representations. Unfortunately, still missing in the literature is a methodology for comparing and selecting feature extraction techniques based on the dissimilarity of the feature representations. In this paper, we propose a framework based on dissimilarity metrics and the intersection of errors, in order to analyze the relationships among feature representations. Each representation is used to train a classifier, and the results are compared by means of a dissimilarity metric. Then, with the aid of Multidimensional Scaling, visual representations are obtained of each of the dissimilarities and used as a guide to identify those that are either complementary or redundant. We applied the proposed framework to the problem of handwritten character and digit recognition. The analysis is followed by the use of an MCS built on the assumption that combining dissimilar feature representations can greatly improve the performance of the system. Experimental results demonstrate that a significant improvement in classification accuracy is achieved due to the complementary nature of the representations. Moreover, the proposed MCS obtained the best results to date for both the MNIST handwritten digit dataset and the Cursive Character Challenge (C-Cube) dataset.     

基于双射变换的脱机手写数字识别方法

针对传统特征提取和分类方法速度慢、稳定性差、识别率低等特点,提出了一种基于外围结构特征提取的手写数字识别方法。该方法多次少量地提取经过双射变换后的图像外围结构特征,对每一次提取的特征结合BP神经网络生成相应的分类器,对不同特征的分类结果进行融合得出手写数字的识别结果。实验结果表明,该特征提取方法实现简单,运算量小,大大提高了脱机手写数字的识别率和效率。     

用于脱机手写数字识别的隐马尔可夫模型

将隐马尔可夫模型(HMM)用于脱机手写数字识别中，系统如何建模是一个值得研究的问题．在考虑手写数字自身特点及特征抽取的基础上，对HMM模型的训练方法及模型参数的选取进行了研究，以提高系统识别率．在银行票据OCR的应用中，与基于神经网络的方法结合使用，使得整张票据的拒识率降低了3％，明显提高了银行票据OCR系统的性能．     

Segmentation and recognition system for unknown-length handwritten digit strings

The segmentation of handwritten digit strings into isolated digits remains a challenging task. The difficulty for recognizing handwritten digit strings is related to several factors such as sloping, overlapping, connecting and unknown length of the digit string. Hence, this paper aims to propose a segmentation and recognition system for unknown-length handwritten digit strings by combining several explicit segmentation methods depending on the configuration link between digits. Three segmentation methods are combined based on histogram of the vertical projection, the contour analysis and the sliding window Radon transform. A recognition and verification module based on support vector machine classifiers allows analyzing and deciding the rejection or acceptance each segmented digit image. Moreover, various submodules are included leading to enhance the robustness of the proposed system. Experimental results conducted on the benchmark dataset show that the proposed system is effective for segmenting handwritten digit strings without prior knowledge of their length comparatively to the state of the art.     

A novel multiset integrated canonical correlation analysis framework and its application in feature fusion

Multiset canonical correlation analysis (MCCA) is difficult to effectively express the integrated correlation among multiple feature vectors in feature fusion. Thus, this paper firstly presents a novel multiset integrated canonical correlation analysis (MICCA) framework. The MICCA establishes a discriminant correlation criterion function of multi-group variables based on generalized correlation coefficient. The criterion function can clearly depict the integrated correlation among multiple feature vectors. Then the paper presents a multiple feature fusion theory and algorithm using the MICCA method. The detailed process of the algorithm is as follows: firstly, extract multiple feature vectors from the same patterns by using different feature extraction methods; then extract multiset integrated canonical correlation features using MICCA; finally form effective discriminant feature vectors through two given feature fusion strategies for pattern classification. The multi-group feature fusion method based on MICCA not only achieves the aim of feature fusion, but also removes the redundancy between features. The experiment results on CENPARMI handwritten Arabic numerals and UCI multiple features database show that the MICCA method has better recognition rates and robustness than the fusion methods based on canonical correlation analysis (CCA) and MCCA.     

Application of multi-layer perceptron neural networks to vision problems

This paper discusses the application of a class of feed-forward Artificial Neural Networks (ANNs) known as Multi-Layer Perceptrons(MLPs) to two vision problems: recognition and pose estimation of 3D objects from a single 2D perspective view; and handwritten digit recognition. In both cases, a multi-MLP classification scheme is developed that combines the decisions of several classifiers. These classifiers operate on the same feature set for the 3D recognition problem whereas different feature types are used for the handwritten digit recognition. The backpropagationlearning rule is used to train the MLPs. Application of the MLP architecture to other vision problems is also briefly discussed.