Handwritten Character Database Research Articles

Handwritten Character Recognition using Enhanced Artificial Neural Network

This study addresses the concerns regarding the performance of Handwritten Character Recognition (HCR) systems, focusing on the classification stage. It is widely acknowledged that the development of the classification model significantly impacts the overall performance of HCR. The problems identified specifically pertain to the classification model, particularly in the context of the Artificial Neural Network (ANN) learning problem, leading to low accuracy in recognizing handwritten characters. The objective of this study is to improve and refine the ANN classification model to achieve better HCR. To achieve this goal, this study proposed a hybrid Flower Pollination Algorithm with Artificial Neural Network (FPA-ANN) classification model for HCR. The FPA is one of the metaheuristic approaches is utilized as an optimization technique to enhance the performance of ANN, particularly by optimizing the network training process of ANN. The experimentation phase involves using the National Institute of Standards and Technology (NIST) handwritten character database. Finally, the proposed FPA-ANN classification model is analyzed based on generated confusion matrix and evaluated performance of the classification model in terms of precision, sensitivity, specificity, F-score and accuracy.

Improved Artificial Neural Network Classification Model based Metaheuristic Optimization for Handwritten Character Recognition

This study addresses the concerns regarding the performance of Handwritten Character Recognition (HCR) systems, focusing on the classification stage. It is widely acknowledged that the development of the classification model significantly impacts the overall performance of HCR. The problems identified specifically pertain to the classification model, particularly in the context of the Artificial Neural Network (ANN) learning problem, leading to low accuracy in recognizing handwritten characters. The objective of this study is to improve and refine the ANN classification model to achieve better HCR. To achieve this goal, this study proposed a hybrid Flower Pollination Algorithm with Artificial Neural Network (FPA-ANN) classification model for HCR. The FPA is one of the metaheuristic approaches is utilized as an optimization technique to enhance the performance of ANN, particularly by optimizing the network training process of ANN. The experimentation phase involves using the National Institute of Standards and Technology (NIST) handwritten character database. Finally, the proposed FPA-ANN classification model is analysed based on generated confusion matrix and evaluated performance of the classification model in terms of precision, sensitivity, specificity, F-score and accuracy.

Development of a Benchmark Odia Handwritten Character Database for an Efficient Offline Handwritten Character Recognition with a Chronological Survey

A good benchmark dataset is a primary requirement in the offline handwritten character recognition (HCR) process. Only three handwritten numerals and alphabet datasets from Odia are publicly accessible for study, although many writers have used several datasets in their experiments. In this article, two tasks are done to address this issue. Those are the following: First, an extensive survey focused on various datasets is provided with the methodologies used in chronological order. The second factor is a solution to the lack of publicly available handwritten characters and numeral datasets. A new dataset of handwritten Odia characters with numerals has been developed. Anyone can access this dataset by sending an email to the authors of the article. This dataset was created with the help of 150 volunteers of various age groups, races, and qualifications. Some homogeneous experiments are conducted using deep learning models to evaluate the consistency of the dataset. One heterogeneous trial has also been performed to estimate the complexities of the characters present in the dataset by comparing them with the existing benchmark datasets.

Fusion of Bilateral 2DPCA Information for Image Reconstruction and Recognition

Being an efficient image reconstruction and recognition algorithm, two-dimensional PCA (2DPCA) has an obvious disadvantage in that it treats the rows and columns of images unequally. To exploit the other lateral information of images, alternative 2DPCA (A2DPCA) and a series of bilateral 2DPCA algorithms have been proposed. This paper proposes a new algorithm named direct bilateral 2DPCA (DB2DPCA) by fusing bilateral information from images directly—that is, we concatenate the projection results of 2DPCA and A2DPCA together as the projection result of DB2DPCA and we average between the reconstruction results of 2DPCA and A2DPCA as the reconstruction result of DB2DPCA. The relationships between DB2DPCA and related algorithms are discussed under some extreme conditions when images are reshaped. To test the proposed algorithm, we conduct experiments of image reconstruction and recognition on two face databases, a handwritten character database and a palmprint database. The performances of different algorithms are evaluated by reconstruction errors and classification accuracies. Experimental results show that DB2DPCA generally outperforms competing algorithms both in image reconstruction and recognition. Additional experiments on reordered and reshaped databases further demonstrate the superiority of the proposed algorithm. In conclusion, DB2DPCA is a rather simple but highly effective algorithm for image reconstruction and recognition.

Tifinagh handwritten character recognition using optimized convolutional neural network

<p><span>Tifinagh handwritten character recognition has been a challenging problem due to the similarity and variability of its alphabets. This paper proposes an optimized convolutional neural network (CNN) architecture for handwritten character recognition. The suggested model of CNN has a multi-layer feed-forward neural network that gets features and properties directly from the input data images. It is based on the newest deep learning open-source Keras Python library. The novelty of the model is to optimize the optical character recognition (OCR) system in order to obtain best performance results in terms of accuracy and execution time. The new optical character recognition system is tested on a customized dataset generated from the amazigh handwritten character database. Experimental results show a good accuracy of the system (99.27%) with an optimal execution time of the classification compared to the previous works.</span></p>

Histogram of Marked Background (HMB) Feature Extraction Method for Arabic Handwriting Recognition

Features extraction is one of the most important steps in handwriting recognition systems. In this paper, we propose a novel features extraction method, which is adapted to the complex nature of Arabic handwriting. The proposed feature called histogram of marked background (HMB) is not considering only ink pixels in a text image, but also uses the background of the image. Each background pixel in the text image was marked according to the repartition of ink pixels in its neighborhood. Feature vectors are extracted by computing histograms from the marked images. Hidden Markov models (HMMs) with Hidden Markov model toolkit (HTK) were used in the recognition process. The experiments were performed on two datasets: IBN SINA database of historical Arabic documents and Isolated Farsi Handwritten Character Database (IFHCDB). The proposed feature in this study produced efficient and promising results for Arabic handwriting recognition, for both isolated characters and for historical documents.

On developing complete character set Meitei Mayek handwritten character database

This paper introduces a large-scale Meitei Mayek handwritten character database. It consists of the complete character set of the script. There are a total of 85,124 character images of 55 character classes with 72,330 and 12,794 images in training and test sets, respectively. The present work focuses on collecting the natural handwriting of individuals by carrying out sample collection in two phases: (a) unconstrained handwriting in the form of answer sheets and classroom notes and (b) tabular forms. A total of nearly 500 individuals have contributed in the development of the database. Recognition of the character images in the database is carried out using different feature descriptors with four popular classifiers, namely KNN, Linear Support Vector Classifier, Random Forest and Support Vector Machine. The paper also proposes a convolutional neural network (CNN) model by enhancing a base CNN architecture by optimally tuning the hyperparameters. Experimental results show that the CNN model can be benchmarked against the concerned database with a test accuracy of 95.56%.

UTHCD: A New Benchmarking for Tamil Handwritten OCR

Handwritten character recognition is a challenging research in the field of document image analysis over many decades due to numerous reasons such as large writing styles variation, inherent noise in data, expansive applications it offers, non-availability of benchmark databases etc. There has been considerable work reported in literature about creation of the database for several Indic scripts but the Tamil script is still in its infancy as it has been reported only in one database [5]. In this paper, we present the work done in the creation of an exhaustive and large unconstrained Tamil Handwritten Character Database (uTHCD). Database consists of around 91000 samples with nearly 600 samples in each of 156 classes. The database is a unified collection of both online and offline samples. Offline samples were collected by asking volunteers to write samples on a form inside a specified grid. For online samples, we made the volunteers write in a similar grid using a digital writing pad. The samples collected encompass a vast variety of writing styles, inherent distortions arising from offline scanning process viz stroke discontinuity, variable thickness of stroke, distortion etc. Algorithms which are resilient to such data can be practically deployed for real time applications. The samples were generated from around 650 native Tamil volunteers including school going kids, homemakers, university students and faculty. The isolated character database will be made publicly available as raw images and Hierarchical Data File (HDF) compressed file. With this database, we expect to set a new benchmark in Tamil handwritten character recognition and serve as a launchpad for many avenues in document image analysis domain. Paper also presents an ideal experimental set-up using the database on convolutional neural networks (CNN) with a baseline accuracy of 88% on test data.

Hybrid Firefly Algorithm with Artificial Neural Network (FA-ANN) Classification Model for Handwritten Character Recognition

This paper acknowledged the issues regarding HCR performances particularly in the classification stage. It is generally agreed that one of the main factors influencing performance in HCR is the development of classification model. As for the classification stage, the problems identified are related to classification model particularly in Artificial Neural Network (ANN) learning problem that results in low accuracy of handwritten character recognition. Thus, the aim of this study is to develop and enhance the ANN classification model in order to identify the handwritten character better. This paper proposed the hybrid Firefly Algorithm with Artificial Neural Network (FA-ANN) classification model for handwritten character. Firefly algorithm acts as optimisation approach in enhancing ANN particularly by optimize network training process of ANN. National Institute of Standards and Technology (NIST) handwritten character database was applied in the experiment.

Handwritten Arabic Characters Recognition using a Hybrid Two-Stage Classifier

Handwritten Arabic character recognition presents a big challenge to researchers in the field of pattern recognition. Arabic characters are characterized by their highly-cursive nature and many of them have a similar appearance. For example, the only difference between some of the alphabet characters is the existence of a number dots above or below the main character shape. This paper proposes a system for isolated off-line handwritten Arabic character recognition using the Discrete Cosine Transform (DCT) as the feature extraction method and a two-stage hybrid classifier. The two stages are a Support Vector Machine (SVM) and a neural network (NN). The first stage is a two-class SVM classifier which classifies a character either a character with dot(s) or without dot(s). The output of this stage is used to extend the feature vector of the character by the class value to give it an extra unique feature. The extend feature vector is fed to a multi-class neural network model to classify the character. The proposed approach is tested on a database of Arabic handwritten characters called AlexU Isolated Alphabet (AIA9K) containing 8,737 character images. The experimental results of the first stage classifier showed a high recognition accuracy rate of 99.14%. The proposed two-stage hybrid classifier obtained an average recognition accuracy rate of 91.84% over all Arabic Alphabet characters.

Local distances preserving based manifold learning

In this paper a local manifold learning method based on the local distances preserving (LDP) is proposed. LDP focuses on extracting and preserving the local distances between the data points. In LDP, the coefficients between each data point and its neighbors are calculated based on the inverse of Euclidean distances between them. Then, a minimization function, which is in accordance with the calculated coefficients, is proposed for calculating the embedded data manifold in the low-dimensional representation space. Matching the way of calculation the coefficients and the proposed minimization function is the main significance of the proposed LDP method. In addition, the proposed LDP method shows less sensitivity to the initial parameters such as the number of neighbors and the value of variance. Also, a stochastic based extension of LDP (SLDP) manifold learning method is proposed. The proposed method is compared with the common manifold learning methods based on the achievable recognition rate and the power of the local distances preserving. The experiments have been done on two different kinds of databases: HODA Persian handwritten character database and ORL face image database. The results demonstrate the suitable performance of LDP and SLDP. Also, the results show the robustness of the proposed method to the number of neighbors and the value of variance parameter. Moreover, the proposed method of calculating the embedded data points in LDP and SLDP has less complexity than the similar local manifold learning methods, Laplacian eigenmaps (LEM) and stochastic LEM (SLEM).

Comparative Study of KNN, SVM and SR Classifiers in Recognizing Arabic Handwritten Characters Employing Feature Fusion

This paper evaluates and compares the performance of K-Nearest Neighbors (KNN), Support Vector Machine (SVM) and Sparse Representation Classifier (SRC) for recognition of isolated Arabic handwritten characters. The proposed framework converts the gray-scale character image to a binary image through Otsu thresholding, and size-normalizes the binary image for feature extraction. Next, we exploit image down-sampling and the histogram of image gradients as features for image classification and apply fusion (combination) of these features to improve the recognition accuracy. The performance of the proposed system is evaluated on Isolated Farsi/Arabic Handwritten Character Database (IFHCDB) – a large dataset containing gray scale character images. Experimental results reveal that the histogram of gradient consistently outperforms down-sampling based features, and the fusion of these two feature sets achieves the best performance. Likewise, SRC and SVM both outperform KNN, with the latter performing the best among the three. Finally, we achieved a commanding accuracy of 93.71% in character recognition with fusion of features classified by SVM, where 92.06% and 91.10% is achieved by SRC and KNN respectively.

A novel nearest interest point classifier for offline Tamil handwritten character recognition

Handwritten character recognition is the most widely used branch of study in image pattern recognition. Tamil, the official language of Tamil Nadu in South India, Sri Lanka, Singapore and Malaysia, has a script which contains many loops and compound characters, with small differences between character classes. Most of the research on offline Tamil handwritten character recognition system was done only on few character classes as it is very difficult to distinguish between minute dissimilarities of large character classes. It is important to design a complete recognition system that can process all character classes of Tamil and distinguish natural variability between inter-class images. Unlike conventional machine learning approaches for pattern recognition problems, we have proposed a nearest interest point classifier, which can choose sufficient and necessary subset of features from a variable length high dimensional feature vector. Since this is a practical problem, in this work, a study on image to image matching is included through feature analysis without using machine learning approaches. The proposed algorithm gave a good recognition accuracy for all the character classes on the standard database available for Tamil, HP Labs offline Tamil handwritten character database. Our proposed classifier produced a recognition accuracy of 90.2% while including the whole dataset. The method has been compared with the standard classifiers and has been proved to be a state-of-the-art performance in recognition of accuracy over the previous results given in the literature.

Single-shot and lensless complex-amplitude imaging with incoherent light based on machine learning

We present a single-shot incoherent light imaging method for simultaneously observing both amplitude and phase without any imaging optics, based on machine learning. In the proposed method, an object with a complex-amplitude field is illuminated with incoherent light and is captured by an image sensor with or without a coded aperture. The complex-amplitude field of the object is reconstructed from a single captured image using a state-of-the-art deep convolutional neural network, which is trained with a large number of input and output pairs. In experimental demonstrations, the proposed method was verified with a handwritten character database, and the effect of a coded aperture printed on an overhead projector film in the reconstruction was examined. Our method has advantages over conventional wavefront sensing techniques using incoherent light, namely simplification of the optical hardware and improved measurement speed. This study shows the importance and practical impact of machine learning techniques in various fields of optical sensing.

A Deep Learning Model of Perception in Color-Letter Synesthesia

Synesthesia is a psychological phenomenon where sensory signals become mixed. Input to one sensory modality produces an experience in a second, unstimulated modality. In “grapheme-color synesthesia”, viewed letters and numbers evoke mental imagery of colors. The study of this condition has implications for increasing our understanding of brain architecture and function, language, memory and semantics, and the nature of consciousness. In this work, we propose a novel application of deep learning to model perception in grapheme-color synesthesia. Achromatic letter images, taken from database of handwritten characters, are used to train the model, and to induce computational synesthesia. Results show the model learns to accurately create a colored version of the inducing stimulus, according to a statistical distribution from experiments on a sample population of grapheme-color synesthetes. To the author’s knowledge, this work represents the first model that accurately produces spontaneous, creative mental imagery characteristic of the synesthetic perceptual experience. Experiments in cognitive science have contributed to our understanding of some of the observable behavioral effects of synesthesia, and previous models have outlined neural mechanisms that may account for these observations. A model of synesthesia that generates testable predictions on brain activity and behavior is needed to complement large scale data collection efforts in neuroscience, especially when articulating simple descriptions of cause (stimulus) and effect (behavior). The research and modeling approach reported here provides a framework that begins to address this need.

Spatial and Textural Aspects for Arabic Handwritten Characters Recognition

The purpose of the present paper is the recognition of handwritten Arabic characters in their isolated form. The specificity of Arabic characters is taken into consideration, each of the proposed feature extraction method integrates one of the two aspects: spatial and textural. In the first step, a modified Bitmap Sampling method is proposed, which converts the character’s images into a binary Matrix and then constructs a Mask for each class. A matching rate is used between the input binary matrix and the masks to determinate the corresponding class. In the second step we investigate the use of an Artificial Neural Network as classifier with the binary matrices as features and then the histograms of Local Binary Patterns to capture the texture aspect of the characters. Finally, the results of these two methods are combined to take into consideration both aspects at the same time. Tested on the Arabic set of the Isolated Farsi Handwritten Character Database, the proposed method has 2.82% error rate

DBAHCL: database for Arabic handwritten characters and ligatures

Unlike Latin, the recognition of Arabic handwritten characters remains at the level of research and experimentation. In fact, it has an undeniable interest in carrying out tasks that may be tedious in certain areas, namely the automatic processing of Arab administrative records, the digitization and safeguarding of the written Arab cultural heritage, and so on. The availability of a database makes it possible to compare objectively the results of the different systems developed in this field. Indeed, the recognition of Arabic handwriting characters still catches the absence of a reference database of Arabic handwritten characters covering all forms of Arabic characters and all possible ligatures of the characters. This article introduces a new database for Arabic handwritten characters and ligatures. This database is designed to cover all forms of Arabic characters, including ligatures. It contains 9900 ligatures and 5500 characters written by 50 writers.

Comprehensive collection for Arabic characters and numbers written by hand

An Optical Character Recognition system for Arabic language should recognize Arabic handwritten words. However, it is difficult to find a freely accessible and comprehensive database of all Arabic words that can be employed for this purpose. Therefore, it is more efficient to divide the Arabic words into sub-words or characters. As there is no comprehensive Arabic handwritten character database that is accessible free of charge, interested researchers can utilize the database developed as a part of this work in recognition system training and output testing.In the present paper, a database is presented containing scanned images of 700 Arabic handwritten characters, Hindi numbers used in Arabic countries, and some special characters utilized in Arabic alphabet, along with their different positions (e.g., standalone, initial, medial and terminal), different sizes, styles and font colors. The aim is to provide sufficient samples for all character shapes for software training, resulting in greater accuracy in the recognition phase.These forms were filled by students of the Applied Sciences College, University of Technology, Baghdad, Iraq and were scanned at the 200, 300, and 600 dpi resolution. A graphical user interface (GUI) software environment is employed to make the manipulation of the created database easier, and provide many image processing functions that are allowed to be built the database easier

A robust statistical set of features for Amazigh handwritten characters

The main problem in the handwritten character recognition systems (HCR) is to describe each character by a set of features that can distinguish it from the other characters. Thus, in this paper, we propose a robust set of features extracted from isolated Amazigh characters based on decomposing the character image into zones and calculate the density and the total length of the histogram projection in each zone. In the experimental evaluation, we test the proposed set of features, to show its performance, with different classification algorithms on a large database of handwritten Amazigh characters. The obtained results give recognition rates that reach 99.03% which we presume good and satisfactory compared to other approaches and show that our proposed set of features is useful to describe the Amazigh characters.

Handwritten Character Recognition Based on the Specificity and the Singularity of the Arabic Language

A good Arabic handwritten recognition system must consider the characteristics of Arabic letters which can be explicit such as the presence of diacritics or implicit such as the baseline information (a virtual line on which cursive text are aligned and/join). In order to find an adequate method of features extraction, we have taken into consideration the nature of the Arabic characters. The paper investigate two methods based on two different visions: one describes the image in terms of the distribution of pixels, and the other describes it in terms of local patterns. Spatial Distribution of Pixels (SDP) is used according to the first vision; whereas Local Binary Patterns (LBP) are used for the second one. Tested on the Arabic portion of the Isolated Farsi Handwritten Character Database (IFHCDB) and using neural networks as a classifier, SDP achieve a recognition rate around 94% while LBP achieve a recognition rate of about 96%.