Handwritten Numeral Databases of Indian Scripts and Multistage Recognition of Mixed Numerals
01 Mar 2009-IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE Computer Society)-Vol. 31, Iss: 3, pp 444-457
TL;DR: P pioneering development of two databases for handwritten numerals of two most popular Indian scripts, a multistage cascaded recognition scheme using wavelet based multiresolution representations and multilayer perceptron classifiers and application for the recognition of mixed handwritten numeral recognition of three Indian scripts Devanagari, Bangla and English.
Abstract: This article primarily concerns the problem of isolated handwritten numeral recognition of major Indian scripts. The principal contributions presented here are (a) pioneering development of two databases for handwritten numerals of two most popular Indian scripts, (b) a multistage cascaded recognition scheme using wavelet based multiresolution representations and multilayer perceptron classifiers and (c) application of (b) for the recognition of mixed handwritten numerals of three Indian scripts Devanagari, Bangla and English. The present databases include respectively 22,556 and 23,392 handwritten isolated numeral samples of Devanagari and Bangla collected from real-life situations and these can be made available free of cost to researchers of other academic Institutions. In the proposed scheme, a numeral is subjected to three multilayer perceptron classifiers corresponding to three coarse-to-fine resolution levels in a cascaded manner. If rejection occurred even at the highest resolution, another multilayer perceptron is used as the final attempt to recognize the input numeral by combining the outputs of three classifiers of the previous stages. This scheme has been extended to the situation when the script of a document is not known a priori or the numerals written on a document belong to different scripts. Handwritten numerals in mixed scripts are frequently found in Indian postal mails and table-form documents.
Citations
More filters
01 Apr 2018
TL;DR: The proposed ensemble learning architecture allows the handwritten patterns to evolve or grow using various parameters that control how the cells interact with each other, and the idea is to captures more variations in a handwritten data set than the typical standalone classifiers or their ensembles.
Abstract: In this study, we propose an ensemble learning architecture called “Cellular Automata Learning and Prediction” (CALP) model, for classification of handwritten patterns. We further propose that every handwritten pattern is an array of living cells or organisms that both interact and are affected by one another. Since the cells impact one another, and have the ability to die and reproduce, we extend this analogy to growth and evolution. Thus every pattern can grow and evolve. We use cellular automata (CA) to model this behavior as it has been used as a default model for various biological systems. Proposed architecture allows the handwritten patterns to evolve or grow using various parameters that control how the cells interact with each other. Then these different evolved patterns are used to train independent classifiers which are then combined together to form an ensemble. The idea is to captures more variations in a handwritten data set than the typical standalone classifiers or their ensembles. The method is applied on 5 handwritten data sets using 5 different classifiers. The experimental results show that our model obtains better classification accuracy on all 5 data sets, even on a small-sized training data. We also compare the performance of CALP with other over-sampling methods.
4 citations
05 Jun 2020
TL;DR: An end-to-end deep convolutional neural network, named as DeepBanglaNet, is proposed to classify Bengali handwritten digits, providing state-of-the-art accuracy of 99.43% on the NumtaDB database and outperforms all other existing models in all traditional evaluation metrics.
Abstract: Classifying handwritten digits is one of the most trending topics of research in the study of the automated text recognition system. The problem is more challenging in the case of Bengali digits due to additional complexities arising from similarity among various digits along with a wide variety of styles of hand-writings. In this paper, an end-to-end deep convolutional neural network, named as DeepBanglaNet, is proposed to classify Bengali handwritten digits. The proposed network utilizes various state-of-the-art optimization algorithms for eliminating vanishing/exploding gradient problems while extracting the global features effectively required for proper recognition of handwritten digits. This results in a very efficient model providing state-of-the-art accuracy of 99.43% on the NumtaDB database and outperforms all other existing models in all traditional evaluation metrics.
4 citations
Cites methods from "Handwritten Numeral Databases of In..."
...Various feature extraction techniques such as Bayesian discriminant approach [5], wavelet-based multi-resolution processing [6] and genetic algorithms [7] have been utilized over the years....
[...]
01 Jan 2020
TL;DR: The main goal of this study is to investigate the capability of several heuristic algorithms, including cuckoo search (CS), gravitational search algorithm (GSA), particle swarm optimization (PSO), and genetic algorithm (GA) in training neural networks for predicting performance and exhaust emissions of the diesel engine fuelled with biodiesel blends.
Abstract: The main goal of this study is to investigate the capability of several heuristic algorithms, including cuckoo search (CS), gravitational search algorithm (GSA), particle swarm optimization (PSO), and genetic algorithm (GA) in training neural networks for predicting performance and exhaust emissions of the diesel engine fuelled with biodiesel blends. The case application is a Hyundai D4CB 2.5 engine together with B0, B10, and B20 biodiesel blends, which are popularly used in Vietnam. The engine process parameters are used as inputs and the outputs include predicted torque and NOx emission. Different predicting models based on neural network trained by different algorithms are developed and investigated. The performance of each model is evaluated and compared using correlation coefficient (R), mean absolute error (MAE), root mean squared error (RMSE), relative absolute error (RAE), and root relative squared error (RRSE). The expected results indicate that neural networks with parameters optimized by heuristic algorithms can be utilized to develop the model for the prediction of performance and exhaust emissions. The study also provided a better understanding of the effects of engine process parameters on performance and exhaust emissions.
4 citations
01 Jan 2020
TL;DR: This paper generates the handwritten character of Devanagari using three-layer CNN having a stride value of two for feature extraction and DCGANs are used which help to generate training data images from the vector representation.
Abstract: As deep learning became popular, the need for huge amounts of data has risen. The major problem faced in deep learning is the data scarcity. Many researchers have done research in areas such as image processing, pattern recognition, artificial intelligence, and cognitive science to solve handwritten character recognition problem but the data availability remains the problem particularly in Indian languages. The main motive of this paper is to generate the handwritten character of Devanagari, for which DCGANs are used which help us to generate training data images from the vector representation. Here, we use three-layer CNN having a stride value of two for feature extraction of the handwritten character. The characters generated look like the character in the original dataset.
4 citations
25 Aug 2013
TL;DR: A new classifier selection method, Sorting-based Dynamic Classifier Ensemble Selection (SDES), which consists of two stages: classifier sorting, and dynamic ensemble selection on sorted classifier sequence, to guarantee high accuracy of the optimal classifier subset.
Abstract: In ensemble learning, a higher accuracy can be achieved by integrating some classifiers instead of all the classifiers. But, it is very difficult to select the best classifier combination which can be seen as an optimization problem, from a pool of classifiers. To deal with this problem, we propose a new classifier selection method, Sorting-based Dynamic Classifier Ensemble Selection (SDES), which consists of two stages: (1) classifier sorting, and (2) dynamic ensemble selection on sorted classifier sequence. In the first stage, classifiers are sorted based on diversity, to avoid searching for the nearest neighbors in dynamic ensemble selection methods and greatly improve the selection efficiency. In the second stage, the optimal subset of classifiers is selected from the sorted classifier sequence based on confidence of test samples, to guarantee high accuracy of the optimal classifier subset. Experimental results have shown the effectiveness and high efficiency of the proposed method.
4 citations
References
More filters
01 Jan 1998
TL;DR: In this article, a graph transformer network (GTN) is proposed for handwritten character recognition, which can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters.
Abstract: Multilayer neural networks trained with the back-propagation algorithm constitute the best example of a successful gradient based learning technique. Given an appropriate network architecture, gradient-based learning algorithms can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters, with minimal preprocessing. This paper reviews various methods applied to handwritten character recognition and compares them on a standard handwritten digit recognition task. Convolutional neural networks, which are specifically designed to deal with the variability of 2D shapes, are shown to outperform all other techniques. Real-life document recognition systems are composed of multiple modules including field extraction, segmentation recognition, and language modeling. A new learning paradigm, called graph transformer networks (GTN), allows such multimodule systems to be trained globally using gradient-based methods so as to minimize an overall performance measure. Two systems for online handwriting recognition are described. Experiments demonstrate the advantage of global training, and the flexibility of graph transformer networks. A graph transformer network for reading a bank cheque is also described. It uses convolutional neural network character recognizers combined with global training techniques to provide record accuracy on business and personal cheques. It is deployed commercially and reads several million cheques per day.
42,067 citations
37,017 citations
Book•
16 Jul 1998
TL;DR: Thorough, well-organized, and completely up to date, this book examines all the important aspects of this emerging technology, including the learning process, back-propagation learning, radial-basis function networks, self-organizing systems, modular networks, temporal processing and neurodynamics, and VLSI implementation of neural networks.
Abstract: From the Publisher:
This book represents the most comprehensive treatment available of neural networks from an engineering perspective. Thorough, well-organized, and completely up to date, it examines all the important aspects of this emerging technology, including the learning process, back-propagation learning, radial-basis function networks, self-organizing systems, modular networks, temporal processing and neurodynamics, and VLSI implementation of neural networks. Written in a concise and fluid manner, by a foremost engineering textbook author, to make the material more accessible, this book is ideal for professional engineers and graduate students entering this exciting field. Computer experiments, problems, worked examples, a bibliography, photographs, and illustrations reinforce key concepts.
29,130 citations
TL;DR: In this paper, it is shown that the difference of information between the approximation of a signal at the resolutions 2/sup j+1/ and 2 /sup j/ (where j is an integer) can be extracted by decomposing this signal on a wavelet orthonormal basis of L/sup 2/(R/sup n/), the vector space of measurable, square-integrable n-dimensional functions.
Abstract: Multiresolution representations are effective for analyzing the information content of images. The properties of the operator which approximates a signal at a given resolution were studied. It is shown that the difference of information between the approximation of a signal at the resolutions 2/sup j+1/ and 2/sup j/ (where j is an integer) can be extracted by decomposing this signal on a wavelet orthonormal basis of L/sup 2/(R/sup n/), the vector space of measurable, square-integrable n-dimensional functions. In L/sup 2/(R), a wavelet orthonormal basis is a family of functions which is built by dilating and translating a unique function psi (x). This decomposition defines an orthogonal multiresolution representation called a wavelet representation. It is computed with a pyramidal algorithm based on convolutions with quadrature mirror filters. Wavelet representation lies between the spatial and Fourier domains. For images, the wavelet representation differentiates several spatial orientations. The application of this representation to data compression in image coding, texture discrimination and fractal analysis is discussed. >
20,028 citations
01 Jan 1988
TL;DR: This chapter contains sections titled: The Problem, The Generalized Delta Rule, Simulation Results, Some Further Generalizations, Conclusion.
Abstract: This chapter contains sections titled: The Problem, The Generalized Delta Rule, Simulation Results, Some Further Generalizations, Conclusion
17,604 citations
Additional excerpts
...Ç...
[...]