Handwritten Word Recognition System Research Articles

Cursive Arabic handwritten word recognition system using majority voting and k-NN for feature descriptor selection

Cursive Arabic handwritten word recognition system using majority voting and k-NN for feature descriptor selection

Arabic Handwritten Word Recognition System Based on the Wavelet Packet Decomposition

This paper attempts to recognize Arabic handwriting based on the Wavelet Packet Decomposition (WPD) using two different classifiers (Support Vector Machine SVM with three kernels and k-Nearest Neighbors K-NN). The proposed approach of recognizing Arabic handwriting contains three major stages including image preprocessing, extracting the features of the image, and classification. Firstly, the diacritics are removed using the opening morphological operation (i.e image preprocessing). Secondly, extracting the structure of the paragraph using the morphological method. Finally, the word image size is converted into a suitable size for the next stages. To extract features from the image, the WPD method was adopted to extract the features of Arabic handwriting as the transformation method of feature space. This extracts the Arabic global features to be classified in the last stage using the SVM with polynomial kernel and K-NN. The proposed approach of recognizing Arabic handwriting was tested on IFN/ENIT dataset by rescaling images into various sizes, 93.7% when the SVM with polynomial kernel is used, K-NN classifier achieved accuracy rate is 88.4%.

Candidate fusion: Integrating language modelling into a sequence-to-sequence handwritten word recognition architecture

Sequence-to-sequence models have recently become very popular for tackling handwritten word recognition problems. However, how to effectively integrate an external language model into such recognizer is still a challenging problem. The main challenge while training a language model is to deal with the language model corpus which is usually different to the one used for training the handwritten word recognition system. Thus, the bias between both word corpora leads to incorrectness on the transcriptions, providing similar or even worse performances on the recognition task. In this work, we introduce Candidate Fusion, a novel way to integrate an external language model to a sequence-to-sequence architecture. Moreover, it provides suggestions from an external language knowledge, as a new input to the sequence-to-sequence recognizer. Hence, Candidate Fusion provides two improvements. On the one hand, the sequence-to-sequence recognizer has the flexibility to not only combine the information from itself and the language model, but also choose the importance of the information provided by the language model. On the other hand, the external language model has the ability to adapt itself to the training corpus and even learn the most common errors produced from the recognizer. Finally, by conducting comprehensive experiments, the Candidate Fusion proves to outperform the state-of-the-art language models for handwritten word recognition tasks.

OFFLINE YORÙBÁ HANDWRITTEN WORD RECOGNITION USING GEOMETRIC FEATURE EXTRACTION AND SUPPORT VECTOR MACHINE CLASSIFIER

Yorùbá language is one of the three main languages that is been spoken in Nigeria. It is a tonal language that carries an accent on the vowel alphabets. There are twenty-five (25) alphabets in Yorùbá language with one of the alphabets a digraph (GB). Due to the difficulty in typing handwritten Yorùbá documents, there is a need to develop a handwritten recognition system that can convert the handwritten texts to digital format. This study discusses the offline Yorùbá handwritten word recognition system (OYHWR) that recognizes Yorùbá uppercase alphabets. Handwritten characters and words were obtained from different writers using the paint application and M708 graphics tablets. The characters were used for training and the words were used for testing. Pre-processing was done on the images and the geometric features of the images were extracted using zoning and gradient-based feature extraction. Geometric features are the different line types that form a particular character such as the vertical, horizontal, and diagonal lines. The geometric features used are the number of horizontal lines, number of vertical lines, number of right diagonal lines, number of left diagonal lines, total length of all horizontal lines, total length of all vertical lines, total length of all right slanting lines, total length of all left-slanting lines and the area of the skeleton. The characters are divided into 9 zones and gradient feature extraction was used to extract the horizontal and vertical components and geometric features in each zone. The words were fed into the support vector machine classifier and the performance was evaluated based on recognition accuracy. Support vector machine is a two-class classifier, hence a multiclass SVM classifier least square support vector machine (LSSVM) was used for word recognition. The one vs one strategy and RBF kernel were used and the recognition accuracy obtained from the tested words ranges between 66.7%, 83.3%, 85.7%, 87.5%, and 100%. The low recognition rate for some of the words could be as a result of the similarity in the extracted features.

Online Handwritten Gujarati Word Recognition

In this article, an online handwritten word recognition system for the Gujarati language is presented by combining strokes, characters, punctuation marks, and diacritics. The authors have used a support vector machine classification algorithm with a radial basis function kernel. The authors used a hybrid features set. The hybrid feature set consists of directional features with curvature data. The authors have used a normalized chain code and zoning-based chain code features. Words are a combination of characters and diacritics. Recognized strokes require post-processing to form a word. The authors have used location-based and mapping rule-based post-processing methods. The authors have achieved an accuracy of 95.3% for individual characters, 91.5% for individual words, and 83.3% for sentences. The average processing time for individual characters is 0.071 seconds.

A GA based hierarchical feature selection approach for handwritten word recognition

Feature selection plays a key role in reducing the dimensionality of a feature vector by discarding redundant and irrelevant ones. In this paper, a Genetic Algorithm-based hierarchical feature selection (HFS) model has been designed to optimize the local and global features extracted from each of the handwritten word images under consideration. In this context, two recently developed feature descriptors based on shape and texture of the word images have been taken into account. Experimentation is conducted on an in-house dataset of 12,000 handwritten word samples written in Bangla script. This database comprises names of 80 popular cities of West Bengal, a state of India. Proposed model not only reduces the feature dimension by nearly 28%, but also enhances the performance of the handwritten word recognition (HWR) technique by 1.28% over the recognition performance obtained with unreduced feature set. Moreover, the proposed HFS-based HWR system performs better in comparison with some recently developed methods on the present dataset.

Ensemble classifier‐based off‐line handwritten word recognition system in holistic approach

This study presents a novel ensemble classifier-based off-line handwritten word recognition system following a holistic approach. Here each handwritten word is recognised using two handcrafted features, namely (i) Arnold transform-based feature that addresses local directional feature which depends on the stroke orientation distribution of cursive word and (ii) oriented curvature-based feature which is basically the histogram of curvelet index and one machine generated feature using deep convolution neural network (DCNN). In this study, a new architecture of DCNN is proposed for handwritten word recognition. These features are recognised by three classifiers separately. Finally, the decision of three classifiers is combined to predict the ultimate word class level. To fuse the decision of individual classifiers, the authors have explored three strategies: (i) vote for strongest decision, (ii) vote for majority decision and (iii) vote for the sum of the decisions. The proposed handwritten word recognition system is tested on three handwritten word databases: (i) CENPARMI database, (ii) IAM database and (iii) ISIHWD database. The performance of the proposed system is promising and comparable to state-of-the-art handwriting recognition systems.

Database corpus for Yoruba handwriting

Non-availability of Yoruba handwritten database has been a major challenge affecting the validation of the Yoruba handwritten recognition system. This paper presents an offline Yoruba handwritten database corpus for validating Yoruba handwritten word recognition system (YHWR). In this research work, 50 medical pathology words were gotten from medical pathology dictionary. The medical pathology words were translated to their Yoruba equivalence and the translated words were hand written by 200 indigenous literate writers with appropriate diacritic signs. The offline handwritten data were scanned using 300 dpi. The database corpus created; converted the scanned images to different image format, different resolutions and different image sizes, to test the effect of different resolutions, different format and image sizes on Yoruba handwritten recognition system. The digitised images were used to create Yourba handwritten database, which, could be used to validate the handwritten recognition system. The database created is considered a raw data that require some level of preprocessing before it can be used for validating the YHWR system.

Offline Arabic Handwriting Recognition System Based on the Combination of Multiple Semi-Continuous HMMs

In this paper, we present a multi-classifier approach for off-line handwritten Arabic word recognition system. The main objective of this paper is to develop a handwriting recognition system that can be learned and applied to different Arabic writing styles. We propose an approach that combines multiple classifiers based on semi-continuous Hidden Markov Model using different feature extraction methods. The following process consists of several phases: pre-processing, extraction of pertinent characteristics and modeling. The role of the pre-processing phase is to prepare the input image text, i.e, binarization, normalization, segmentation and skeletonization. The obtained images are then used to extract features using a mixture of geometrical and statistical characteristics, namely, the intensities of gray level of the pixel, the densities and the concavities of the pixels, the VH2D projections and the invariants Hu moments. The modeling phase is based on the Hidden Markov Model using the HTK tools for the training and the recognition phase. Each character is modeled by a semi-continuous HMMs, and each set of feature has its own HMM. To improve the performance of our Arabic handwriting recognition system, we propose to combine parallel methods of HMMs having the same architecture, but training phase using four different types of primitive vectors. Our system was evaluated using the ENIT/IFN the base Arabic data. Results Obtained show that the combination of four semi-continuous HMM classifiers gives a significant improvement of our off-line handwriting recognition system compared to results obtained when using individual classifiers.

A Novel Approach of Skew Correction for Online Handwritten Words

Segmentation of a word into basic characters or strokes is an essential and necessary step for character recognition in many handwritten word recognition systems. The one of the major difficulties in character segmentation is the existence of the skew in the handwritten word. But skew detection in the bangla handwritten word is difficult because of its shape variability of the characters as well as larger number of character classes. If the skew correction is done successfully then the character segmentation of the word will be more perfect and as a consequence the percentage of the correct word recognition will be higher. In this paper, we propose a novel method for skew detection and skew correction of online Bengali handwritten word through holistic approach. This approach works based on center of gravity of left part and right part of a handwritten word. After finding the center of gravity it calculates the angle of the line which connected the two gravity centers in relation to horizontal line. Then Rotates the word clockwise by the angle θ if θ 90o. All the pixel moves to the particular angle to correct the skew. The algorithm has been verified on a database of 3000 Bengali word data collected from different people of different age group and it gives 92.22% accuracy on word data from the proposed system. General Terms Pattern Recognition.

Freeman Chain Code Contour Processing for Handwritten Isolated Arabic Characters Recognition

The Arabic characters are being used in various languages. Recognition of handwritten characters of Arabic alphabet set is an important area of research. The work on recognition of Handwritten Isolated Arabic Characters (HIAC) is still an open research problem and it has numerous applications. Machine reading of optically scanned text is usually called optical Character recognition (OCR). In this paper we present an OCR for Handwritten Isolated Arabic Characters. Basic Characters are recognized by Freeman chain code. The proposed method obtains the contour of the character and then generates a Freeman Chain Code for contoured character. The obtained Freeman chain code is unique for handwritten isolated characters. The present method is based on template matching to recognize handwritten printed isolated Arabic characters. It was trained and validated on 200 images (consisting of 7400 Arabic characters written by 18 writers). Our experimentation observed the overall recognition rate is 95%. It is carried out in order to improve the rate and the performance of an Arabic handwritten word recognition system. The proposed system has been implemented and tested on Matlab R2008b environment.

Arabic Handwritten Word Recognition Using HMMs with Explicit State Duration

We describe an offline unconstrained Arabic handwritten word recognition system based on segmentation-free approach and discrete hidden Markov models (HMMs) with explicit state duration. Character durations play a significant part in the recognition of cursive handwriting. The duration information is still mostly disregarded in HMM-based automatic cursive handwriting recognizers due to the fact that HMMs are deficient in modeling character durations properly. We will show experimentally that explicit state duration modeling in the HMM framework can significantly improve the discriminating capacity of the HMMs to deal with very difficult pattern recognition tasks such as unconstrained Arabic handwriting recognition. In order to carry out the letter and word model training and recognition more efficiently, we propose a new version of the Viterbi algorithm taking into account explicit state duration modeling. Three distributions (Gamma, Gauss, and Poisson) for the explicit state duration modeling have been used, and a comparison between them has been reported. To perform word recognition, the described system uses an original sliding window approach based on vertical projection histogram analysis of the word and extracts a new pertinent set of statistical and structural features from the word image. Several experiments have been performed using the IFN/ENIT benchmark database and the best recognition performances achieved by our system outperform those reported recently on the same database.

MIXED DISCRIMINANT TRAINING OF HYBRID ANN/HMM SYSTEMS FOR ONLINE HANDWRITTEN WORD RECOGNITION

Online handwritten word recognition systems usually rely on Hidden Markov Models (HMMs), which are effective under many circumstances, but suffer some major limitations in real world applications. Artificial neural networks (ANN) appear to be a promising alternative, however they failed to model sequence data such as online handwriting due to their variable lengths. As a consequence, by combining HMMs and ANN, we can expect to take advantage of the robustness and flexibility of the HMMs generative models and of the discriminative power of the ANN. Training such a hybrid system is not straightforward, this is why so few attempts are encountered in literature. We compare several different training schemes: maximum likelihood (ML) and maximum mutual information (MMI) criteria in the framework of online handwriting recognition with a global optimization approach defined at the word level. A new generic criterion mixing generative model and discriminant trainings is proposed, it allows to train a multistate TDNN-HMM system directly at the word level. This architecture is based on an analytical approach with an implicit segmentation. To control the implicit segmentation and to initialize correctly the system without bootstrapping with another recognition system, we have defined a process that constraints the segmentation path and a measure called Average Segmentation Rate (ASR). Recognition experiments on the online IRONOFF database demonstrated the interest of the generic training criterion and the control of the implicit segmentation.

An investigation of the modified direction feature for cursive character recognition

This paper describes and analyses the performance of a novel feature extraction technique for the recognition of segmented/cursive characters that may be used in the context of a segmentation-based handwritten word recognition system. The modified direction feature (MDF) extraction technique builds upon the direction feature (DF) technique proposed previously that extracts direction information from the structure of character contours. This principal was extended so that the direction information is integrated with a technique for detecting transitions between background and foreground pixels in the character image. In order to improve on the DF extraction technique, a number of modifications were undertaken. With a view to describe the character contour more effectively, a re-design of the direction number determination technique was performed. Also, an additional global feature was introduced to improve the recognition accuracy for those characters that were most frequently confused with patterns of similar appearance. MDF was tested using a neural network-based classifier and compared to the DF and transition feature (TF) extraction techniques. MDF outperformed both DF and TF techniques using a benchmark dataset and compared favourably with the top results in the literature. A recognition accuracy of above 89% is reported on characters from the CEDAR dataset.

Recognition and verification of unconstrained handwritten words

This paper presents a novel approach for the verification of the word hypotheses generated by a large vocabulary, offline handwritten word recognition system. Given a word image, the recognition system produces a ranked list of the N-best recognition hypotheses consisting of text transcripts, segmentation boundaries of the word hypotheses into characters, and recognition scores. The verification consists of an estimation of the probability of each segment representing a known class of character. Then, character probabilities are combined to produce word confidence scores which are further integrated with the recognition scores produced by the recognition system. The N-best recognition hypothesis list is reranked based on such composite scores. In the end, rejection rules are invoked to either accept the best recognition hypothesis of such a list or to reject the input word image. The use of the verification approach has improved the word recognition rate as well as the reliability of the recognition system, while not causing significant delays in the recognition process. Our approach is described in detail and the experimental results on a large database of unconstrained handwritten words extracted from postal envelopes are presented.

Optimization of Weights in a Multiple Classifier Handwritten Word Recognition System Using a Genetic Algorithm

Automatic handwritten text recognition by computer has a number of interesting applications. However, due to a great variety of individual writing styles, the problem is very difficult and far from being solved. Recently, a number of classifier creation methods, known as ensemble methods, have been proposed in the field of machine learning. They have shown improved recognition performance over single classifiers. For the combination of these classifiers many methods have been proposed in the literature. In this paper we describe a weighted voting scheme where the weights are obtained by a genetic algorithm.

Large vocabulary off-line handwriting recognition: A survey

Considerable progress has been made in handwriting recognition technology over the last few years. Thus far, handwriting recognition systems have been limited to small and medium vocabulary applications, since most of them often rely on a lexicon during the recognition process. The capability of dealing with large lexicons, however, opens up many more applications. This article will discuss the methods and principles that have been proposed to handle large vocabularies and identify the key issues affecting their future deployment. To illustrate some of the points raised, a large vocabulary off-line handwritten word recognition system will be described.

Neural networks with enhanced outlier rejection ability for off-line handwritten word recognition

For a segmentation and dynamic programming-based handwritten word recognition system, outlier rejection at the character level can improve word recognition performance because it reduces the chances that erroneous combinations of segments result in high word confidence values. We studied the multilayer perceptron (MLP) and a variant of radial basis function network (RBF) with the goal to use them as character level classifiers that have enhanced outlier rejection ability. The variant of the RBF uses principal component analysis (PCA) on the clusters defined by the nodes in the hidden layer. It was also trained with and without a regularization term that was aimed at minimizing the variances of the nodes in the hidden layer. Our experiments on handwritten word recognition showed: (1) In the case of MLPs, using more hidden nodes than that required for classification and including outliers in the training data can improve outlier rejection performance; (2) in the case of PCA–RBFs, training with the regularization term and no outlier can achieve performance very close to training with outliers. These results are both interesting. Result (1) is of interest because it is well known that minimizing the number of parameters, and therefore keeping the number of hidden units low, should increase the generalization capability. On the other hand, using more hidden units increases the chances of creating closed decision regions, as predicted by the theory in Gori and Scarselli (IEEE Trans. PAMI 20 (11) (1998) 1121). Result (2) is a strong statement in support of the use of regularization terms for the training of RBF-type neural networks in problems such as handwriting recognition for which outlier rejection is important. Additional tests on combining MLPs and PCA-RBF networks showed the potential to improve word recognition performance by exploiting the complementarity of these two kinds of neural networks.

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.

Unconstrained Farsi handwritten word recognition using fuzzy vector quantization and hidden Markov models

An unconstrained Farsi handwritten word recognition system based on fuzzy vector quantization (FVQ) and hidden Markov model (HMM) for reading city names in postal addresses is presented. Preprocessing techniques including binarization, noise removal, slope correction and baseline estimation are described. Each word image is represented by its contour information. The histogram of chain code slopes of the image strips (frames), scanned from right to left by a sliding window, is used as feature vectors. Fuzzy c-means (FCM) clustering is used for generating a fuzzy codebook. A separate HMM is trained by modified Baum–Welch algorithm for each city name. A test image is recognized by finding the best match (likelihood) between the image and all of the HMM word models using forward algorithm. Experimental results show the advantages of using FVQ/HMM recognizer engine instead of conventional discrete HMMs.