Problem Of Handwritten Character Recognition Research Articles

Enhanced Recognition of Handwritten Marathi Compound Characters using CNN-SVM Hybrid Approach

This study presents a hybrid recognition system for multi-class compound Marathi characters, which addresses the problem of handwritten Marathi character recognition. The methodology efficiently bridges the gap between feature extraction and classification by integrating a Convolutional Neural Network (CNN) and Support Vector Machine (SVM). The first step is gathering and preprocessing a wide range of handwritten Marathi compound characters that are written in different styles. Using conventional supervised learning methods, the CNN is trained on this dataset, paying special attention to data augmentation and validation in order to reduce overfitting. High-level features taken from the final fully connected layer of the CNN are fed into an SVM classifier in the next step. By using these features in its training, the SVM improves prediction accuracy. For multi-class classification, the one-vs-all method is used. The hybrid CNN-SVM algorithm demonstrates its effectiveness in the crucial phases of feature extraction and classification by identifying handwritten compound Marathi characters with remarkable accuracy. Evaluation metrics, such as accuracy, precision, recall, F1-score, and confusion matrix analysis, are employed in the process of evaluating the effectiveness of the model. This assessment is carried out on a different testing dataset, offering a thorough examination of the model's functionality. The proposed algorithm demonstrates its superior performance and potential for improved character recognition by achieving training accuracy of 98.60% and validation accuracy of 97.69%. The development of handwriting recognition systems has benefited greatly from this research, especially when it comes to intricate scripts like Marathi. The suggested hybrid algorithm shows encouraging outcomes and has a great deal of potential for use in document processing, natural language comprehension, and character recognition in languages that use the Marathi script. Subsequent efforts will centre on refining the model and investigating ensemble methods to increase the robustness and accuracy of recognition.

Fast Extreme Learning Machine for Berber Handwritten Latin Script

This article deals with the problem of Berber handwritten character recognition using Extreme Learning Machine. This paradigm has gained significant attention in pattern recognition field thanks to its efficient learning speed and its high accuracy. In this paper, we have used a fast Extreme Learning Machine to recognize efficiently the Latin Berber characters. So, the proposed ELM has been trained over a Berber-MNIST dataset containing images of Amazigh alphabets. This algorithm learns much faster than traditional popular learning algorithms thanks to the use of JAX library which contains several functions to reduce the execution time of our solution. The simulation results show that the handwritten recognition system based on our developed extreme learning machine decreases computational cost and reduces the time required for the whole recognition process. Furthermore, the developed ELM achieves a high performance in terms of recognition accuracy.

A Fusion-Based Hybrid-Feature Approach for Recognition of Unconstrained Offline Handwritten Hindi Characters

Hindi is the official language of India and used by a large population for several public services like postal, bank, judiciary, and public surveys. Efficient management of these services needs language-based automation. The proposed model addresses the problem of handwritten Hindi character recognition using a machine learning approach. The pre-trained DCNN models namely; InceptionV3-Net, VGG19-Net, and ResNet50 were used for the extraction of salient features from the characters’ images. A novel approach of fusion is adopted in the proposed work; the DCNN-based features are fused with the handcrafted features received from Bi-orthogonal discrete wavelet transform. The feature size was reduced by the Principal Component Analysis method. The hybrid features were examined with popular classifiers namely; Multi-Layer Perceptron (MLP) and Support Vector Machine (SVM). The recognition cost was reduced by 84.37%. The model achieved significant scores of precision, recall, and F1-measure—98.78%, 98.67%, and 98.69%—with overall recognition accuracy of 98.73%.

Handwritten Bangla Numerical Digit Recognition Using Fine Regulated Deep Neural Network

The recognition of handwritten Bangla digit is providing significant progress on optical character recognition (OCR). It is a very critical task due to the similar pattern and alignment of handwriting digits. With the progress of modern research on optical character recognition, it is reducing the complexity of the classification task by several methods, a few problems encounter during recognition and wait to be solved with simpler methods. The modern emerging field of artificial intelligence is the Deep Neural Network, which promises a solid solution to these few handwritten recognition problems. This paper proposed a fine regulated deep neural network (FRDNN) for the handwritten numeric character recognition problem that uses convolutional neural network (CNN) models with regularization parameters which makes the model generalized by preventing the overfitting. This paper applied Traditional Deep Neural Network (TDNN) and Fine regulated deep neural network (FRDNN) models with a similar layer experienced on BanglaLekha-Isolated databases and the classification accuracies for the two models were 96.25% and 96.99%, respectively over 100 epochs. The network performance of the FRDNN model on the BanglaLekha-Isolated digit dataset was more robust and accurate than the TDNN model and depend on experimentation. Our proposed method is obtained a good recognition accuracy compared with other existing available methods.

An Optimized Deep Residual Network with a Depth Concatenated Block for Handwritten Characters Classification

Even though much advancements have been achieved with regards to the recognition of handwritten characters, researchers still face difficulties with the handwritten character recognition problem, especially with the advent of... | Find, read and cite all the research you need on Tech Science Press

Hybridizing Evolutionary Computation and Deep Neural Networks: An Approach to Handwriting Recognition Using Committees and Transfer Learning

Neuroevolution is the field of study that uses evolutionary computation in order to optimize certain aspect of the design of neural networks, most often its topology and hyperparameters. The field was introduced in the late-1980s, but only in the latest years the field has become mature enough to enable the optimization of deep learning models, such as convolutional neural networks. In this paper, we rely on previous work to apply neuroevolution in order to optimize the topology of deep neural networks that can be used to solve the problem of handwritten character recognition. Moreover, we take advantage of the fact that evolutionary algorithms optimize a population of candidate solutions, by combining a set of the best evolved models resulting in a committee of convolutional neural networks. This process is enhanced by using specific mechanisms to preserve the diversity of the population. Additionally, in this paper, we address one of the disadvantages of neuroevolution: the process is very expensive in terms of computational time. To lessen this issue, we explore the performance of topology transfer learning: whether the best topology obtained using neuroevolution for a certain domain can be successfully applied to a different domain. By doing so, the expensive process of neuroevolution can be reused to tackle different problems, turning it into a more appealing approach for optimizing the design of neural networks topologies. After evaluating our proposal, results show that both the use of neuroevolved committees and the application of topology transfer learning are successful: committees of convolutional neural networks are able to improve classification results when compared to single models, and topologies learned for one problem can be reused for a different problem and data with a good performance. Additionally, both approaches can be combined by building committees of transferred topologies, and this combination attains results that combine the best of both approaches.

Building efficient CNN architecture for offline handwritten Chinese character recognition

Deep convolutional networks based methods have brought great breakthrough in images classification, which provides an end-to-end solution for handwritten Chinese character recognition(HCCR) problem through learning discriminative features automatically. Nevertheless, state-of-the-art CNNs appear to incur huge computation cost, and require the storage of a large number of parameters especially in fully connected layers, which is difficult to deploy such networks into alternative hardware device with the limit of computation amount. To solve the storage problem, we propose a novel technique called Global Weighted Arverage Pooling for reducing the parameters in fully connected layer without loss in accuracy. Besides, we implement a cascaded model in single CNN by adding mid output layer to complete recognition as early as possible, which reduces average inference time significantly. Experiments were performed on the ICDAR-2013 offline HCCR dataset, and it is found that the proposed approach only needs 6.9ms for classfying a chracter image on average, and achieves the state-of-the-art accuracy of 97.1% while requiring only 3.3MB for storage.

Integrating scattering feature maps with convolutional neural networks for Malayalam handwritten character recognition

Convolutional neural network (CNN)-based deep learning architectures are the state-of-the-art in image-based pattern recognition applications. The receptive filter fields in convolutional layers are learned from training data patterns automatically during classifier learning. There are number of well-defined, well-studied and proven filters in the literature that can extract informative content from the input patterns. This paper focuses on utilizing scattering transform-based wavelet filters as the first-layer convolutional filters in CNN architecture. The scattering networks are generated by a series of scattering transform operations. The scattering coefficients generated in first few layers are effective in capturing the dominant energy contained in the input data patterns. The present work aims at replacing the first-layer convolutional feature maps in CNN architecture with scattering feature maps. This architecture is equivalent to utilizing scattering wavelet filters as the first-layer receptive fields in CNN architecture. The proposed hybrid CNN architecture experiments the Malayalam handwritten character recognition which is one of the challenging multi-class classification problems. The initial studies confirm that the proposed hybrid CNN architecture based on scattering feature maps could perform better than the equivalent self-learning architecture of CNN on handwritten character recognition problems.

Convolutional Neural Networks for Handwritten Javanese Character Recognition

Convolutional neural network (CNN) is state-of-the-art method in object recognition task. Specialized for spatial input data type, CNN has special convolutional and pooling layers which enable hierarchical feature learning from the input space. For offline handwritten character recognition problem such as classifying character in MNIST database, CNN shows better classification result than any other methods. By leveraging the advantages of CNN over character recognition task, in this paper we developed a software which utilizes digital image processing methods and CNN module for offline handwritten Javanese character recognition. The software performs image segmentation process using contour and Canny edge detection with OpenCV library over captured handwritten Javanese character image. CNN will classify the segmented image into 20 classes of Javanese letters. For evaluation purposes, we compared CNN to multilayer perceptron (MLP) on classification accuracy and training time. Experiment results show that CNN model testing accuracy outperforms MLP accuracy although CNN needs more training time than MLP.

MDP Feature Extraction Technique for Offline Handwritten Gurmukhi Character Recognition

Character recognition is intricate work because of the various writing styles of different individuals. Most of the published work on handwritten character recognition problems deals with statistical features, and a few works deal with structural features, in general, and Gurmukhi script, in particular. In the present work, we propose a methodology for offline handwritten Gurmukhi character recognition by using a modified division points (MDP) feature extraction technique. We also compare this technique with other recently used feature extraction techniques, namely zoning features, diagonal features, directional features, intersection and open end points features, and transition features. To select a representative set of features is the most significant task for a character recognition system. After feature extraction, the classification stage makes use of the features extracted in the previous stage to recognize the character. In this work, we used linear-support vector machines (linear-SVM), k-nearest neighbor (k-NN), and multilayer perceptron (MLP) classifiers for recognition. For experimental analysis, we used 10,500 samples of the isolated, offline, handwritten, basic 35 akhars of Gurmukhi script. The proposed system achieved a maximum recognition accuracy of 84.57%, 85.85% and 89.20% with linear-SVM, MLP and k-NN classifiers, respectively, with a five-fold cross validation technique.

Evaluation of weighted Fisher criteria for large category dimensionality reduction in application to Chinese handwriting recognition

To improve the class separability of Fisher linear discriminant analysis (FDA) for large category problems, we investigate the weighted Fisher criterion (WFC) by integrating weighting functions for dimensionality reduction. The objective of WFC is to maximize the sum of weighted distances of all class pairs. By setting larger weights for the most confusable classes, WFC can improve the class separation while the solution remains an eigen-decomposition problem. We evaluate five weighting functions in three different weighting spaces in a typical large category problem of handwritten Chinese character recognition. The weighting functions include four based on existing methods, namely, FDA, approximate pairwise accuracy criterion (aPAC), power function (POW), confused distance maximization (CDM), and a new one based on K-nearest neighbors (KNN). All the weighting functions can be calculated in the original feature space, low-dimensional space, or fractional space. Our experiments on a 3,755-class Chinese handwriting database demonstrate that WFC can improve the classification accuracy significantly compared to FDA. Among the weighting functions, the KNN method in the original space is the most competitive model which achieves significantly higher classification accuracy and has a low computational complexity. To further improve the performance, we propose a nonparametric extension of the KNN method from the class level to the sample level. The sample level KNN (SKNN) method is shown to outperform significantly other methods in Chinese handwriting recognition such as the locally linear discriminant analysis (LLDA), neighbor class linear discriminant analysis (NCLDA), and heteroscedastic linear discriminant analysis (HLDA).

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.

Handwritten Character Recognition using Different Kernel based SVM Classifier and MLP Neural Network (A COMPARISON)

Neural Networks and SVM are recently being used in various kind of pattern recognition. As humans, it is easy to recognize numbers, letters, voices, and objects, to name a few. However, making a machine solve these types of problems is a very difficult task .Character Recognition has been an active area of research in the field of image processing and pattern recognition and due to its diverse applicable environment, it continues to be a challenging research topic. It has numerous applications which include, reading aid for blind, bank cheques and conversion of any hand written document into structural text form. In this paper an attempt is made to recognized handwritten character using the multi layer feed forward back propagation neural network without feature extraction and SVM classifier. Character data is used for training the neural network and SVM. The trained network is used for classification and recognition. For the neural network, each character is resized into 70x50 pixels, which is directly subjected to training. That is, each resized character has 3500 pixels and these pixels are taken as features for training the neural network. For the SVM classifier recognition model is divided in two phases namely, training and testing phase. In the training phase 25 features are extracted from each character and these features are used to train the SVM. In the testing phase SVM classifier is used to recognize the characters. The results show that by applying the proposed system, we reached a high accuracy for the problem of handwritten character recognition.

Handwritten Character Recognition Using Multiresolution Technique and Euclidean Distance Metric

In the present paper, the problem of handwritten character recognition has been tackled with multiresolution technique using discrete wavelet transform (DWT) and Euclidean distance metric (EDM). The technique has been tested and found to be more accurate and faster. Characters is classified into 26 pattern classes based on appropriate properties. Features of the handwritten character images are extracted by DWT used with appropriate level of multiresolution technique, and then each pattern class is characterized by a mean vector. Distances from input pattern vector to all the mean vectors are computed by EDM. Minimum distance determines the class membership of input pattern vector. The proposed method provides good recognition accuracy of 90% for handwritten characters even with fewer samples.

A large margin approach for writer independent online handwriting classification

This paper proposes a new approach for classifying multivariate time-series with applications to the problem of writer independent online handwritten character recognition. Each time-series is approximated by a sum of piecewise polynomials in a suitably defined Reproducing Kernel Hilbert Space (RKHS). Using the associated kernel function a large margin classification formulation is proposed which can discriminate between two such functions belonging to the RKHS. The associated problem turns out to be an instance of convex quadratic programming. The resultant classification scheme applies to many time-series discrimination tasks and shows encouraging results when applied to online handwriting recognition tasks.

Parallel compact integration in handwritten Chinese character recognition

In this paper, a new parallel compact integration scheme based on multi-layer perceptron (MLP) networks is proposed to solve handwritten Chinese character recognition (HCCR) problems. The idea of metasynthesis is applied to HCCR, and compact MLP network classifier is defined. Human intelligence and computer capabilities are combined together effectively through a procedure of two-step supervised learning. Compared with previous integration schemes, this scheme is characterized with parallel compact structure and better performance. It provides a promising way for applying MLP to large vocabulary classification.

Domain learning using Choquet integral-based morphological shared weight neural networks

Morphological shared weight networks (MSNNs) have been applied to many different problem domains, such as discriminating textures, target and hand written character recognition problems. MSNNs use morphological hit-and-miss transforms (HMT) as the activation functions in the feature extraction layer. However, conventional morphological filters have certain drawbacks. They are not robust and therefore are sensitive to noise. They may not tolerate small changes in gray values and shape. On the other hand, Choquet integral-based morphological operations (CMOs), a natural extension of classical morphological operations, are less sensitive to degradations in an image. The MSNN architecture is extended using CMOs in place of HMTs. These networks are referred to as Choquet morphological shared-weight neural networks (CMSNN). In a related paper, we compared the MSNN and CMSNN by extensive experimentation on the real world problem of land mine detection. In this paper, we discuss the problem of domain learning, which is related to feature importance. We provide examples of successes and failures of generalized mathematical morphology and the Choquet integral. These results are interesting, not only for purposes of robustness, but when viewed in the context of determining more valuable information sources.

Symbolic vs. connectionist learning: an experimental comparison in a structured domain

During the last two decades, the attempts to find effective solutions to the problem of learning any kind of structured information have been splitting the scientific community. A "holy war" has been fought between the advocates of a symbolic approach to learning and the advocates of a connectionist approach. One of the most repeated claims of the symbolic party has been that symbolic methods are able to cope with structured information while connectionist ones are not. However, in the last few years, the possibility of employing connectionist methods for structured data has been widely investigated and several approaches have been proposed. A novel algorithm for learning structured descriptions, ascribable to the category of symbolic techniques, is proposed. It faces the problem directly in the space of graphs by defining the proper inference operators, as graph generalization and graph specialization, and obtains general and consistent prototypes with a low computational cost with respect to other symbolic learning systems. The proposed algorithm is compared with a recent connectionist method for learning structured data (P. Frasconi et al., 1998), with reference to a problem of handwritten character recognition from a standard database on the Web. The orthogonality of the two approaches strongly suggests their combination in a multiclassifier system so as to retain the strengths of both of them, while overcoming their weaknesses. The results on an experimental case study demonstrated that the adoption of a parallel combination scheme of the two algorithms could improve the recognition performance by about 10 percent. A truce or an alliance between the symbolic and the connectionist worlds?.

Neural networks with hybrid morphological/rank/linear nodes: a unifying framework with applications to handwritten character recognition

In this paper, the general class of morphological/rank/linear (MRL) multilayer feed-forward neural networks (NNs) is presented as a unifying signal processing tool that incorporates the properties of multilayer perceptrons (MLPs) and morphological/rank neural networks (MRNNs). The fundamental processing unit of MRL-NNs is the MRL-filter, where the combination of inputs in every node is formed by hybrid linear and nonlinear (of the morphological/rank type) operations. For its design we formulate a methodology using ideas from the back-propagation algorithm and robust techniques to circumvent the non-differentiability of rank functions. Extensive experimental results are presented from the problem of handwritten character recognition, which suggest that MRL-NNs not only provide better or similar performance when compared to MLPs but also can be trained faster. The MRL-NNs are a broad interesting class of nonlinear systems with many promising applications in pattern recognition and signal/image processing.

A TRULY 2-D HIDDEN MARKOV MODEL FOR OFF-LINE HANDWRITTEN CHARACTER RECOGNITION

In recent years, there have been several attempts to extend one-dimensional hidden Markov model (HMM) to two-dimension. Unfortunately, the previous efforts have not yet achieved a truly two-dimensional (2-D) HMM because of both the difficulty in establishing a suitable 2-D model and its computational complexity. This paper presents a new framework for the recognition of handwritten characters using a truly 2-D model: hidden Markov mesh random field (HMMRF). The HMMRF model is an extension of a 1-D HMM to 2-D that can provide a better description of the 2-D nature of characters. The application of HMMRF model to character recognition necessitates two phases: the training phase and the decoding phase. Our optimization criterion for training and decoding is based on the maximum, marginal a posteriori probability. We also develop a new formulation of parameter estimation for character recognition. Computational concerns in 2-D, however, necessitate certain simplifying assumptions on the model and approximations on the implementation of the estimation algorithm. In particular, the image is represented by a third-order MMRF and the proposed estimation algorithm is applied over the look-ahead observations rather than over the entire image. Thus, the formulation is derived from the extension of the look-ahead technique devised for a real-time decoding. Experimental results confirm that the proposed approach offers a great potential for solving difficult handwritten character recognition problems under reasonable modeling assumptions.