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
TL;DR: The robustness and design procedure of the proposed model created a cost-effective extension for recognition of handwritten numerals in other languages, and used transfer-learning in the proposed system to enhance the image quality and consequently the recognition performance.
16 citations
02 Mar 2015
TL;DR: A feature extraction method is proposed for numerals of Indian languages and it has been observed that structural feature are having an edge over the statistical feature used so far.
Abstract: The performance of any machine based recognition system heavily depends on the types of features used. More accurate the features extracted are, better is the chance of getting enhance performance in the recognition system. With this aim in mind a feature extraction method is proposed for numerals of Indian languages. It has been observed that structural feature are having an edge over the statistical feature used so far. Orientations of strokes that create a numeral play the most important role in the recognition. Orientations of pixels that create strokes are estimated from the image of the numerals and used as the main component of the proposed feature set. The efficiency of the feature set is then tested using a linear Support Vector Machine classifier. Results reported for large databases of Devanagari and Gujarati numerals are comparable with the highest recognition rate reported so far.
16 citations
Cites background from "Handwritten Numeral Databases of In..."
...The current state of the art research on digit recognition are available in [1], [2]....
[...]
01 Jan 2016
TL;DR: The performance of two architecture of Neural Networks are compared for handwritten Devanagari character recognition and the improved result is obtained for standard character benchmarking datasets.
Abstract: The performance of two architecture of Neural Networks are compared for handwritten Devanagari character recognition. The first one is the fully connected Feed-forward Neural Network and the second one is deep Convolutional Neural Network. Deep learning is basically a biologically inspired technique based on human brain. A part of brain called neocortex is having layered architecture. The advantage of using CNN is that it does not require complex preprocessing or feature extraction algorithm. Image pixels are the input for the two networks. We obtained the improved result for standard character benchmarking datasets.
16 citations
24 Aug 2013
TL;DR: This work uses an ensemble of MLP classifiers having different hidden layer sizes and results of their classification are combined based on Adaboost technique, and studies use of boosting as a solution to this problem of using MLP as a classifier in real-life applications.
Abstract: In this article, we present our recent study of offline recognition of handwritten numerals of three Indian scripts -- Devanagari, Bangla and Oriya. Here, we propose a novel approach to combination of multiple MLP classifiers with varying number of hidden nodes based on Adaboost technique. In this recognition study, we used Zernike moment features of different orders. We obtained classification results corresponding to a number of orders of this moment function and the best classification result for each script was obtained when the feature vector consists of moment values up to the order 8. It is well-known that the classification performance of an MLP largely depends on the choice of the number of hidden nodes. In the present work, we studied use of boosting as a solution to this problem of using MLP as a classifier in real-life applications. Here, we use an ensemble of MLP classifiers having different hidden layer sizes and results of their classification are combined based on Adaboost technique. Classification results have been provided using publicly available databases [1] of offline handwritten numeral images of three Indian scripts.
15 citations
Cites background from "Handwritten Numeral Databases of In..."
...Several handwriting recognition studies of major Indian scripts such as Devanagari and Bangla are also found in the literature [4]....
[...]
...Although ANN classifiers may individually perform efficiently, more sophistication have been studied to achieve higher accuracies [4, 10]....
[...]
...Use of multiple classifiers for obtaining high recognition accuracies has been a common practice in pattern recognition research and multiple MLPs had been used in a number of handwriting recognition studies [4, 10]....
[...]
01 Nov 2015
TL;DR: SVM recognition output of DDD features combined with the SVM output of GSC features improves the final recognition accuracy significantly and is obtained on a large handwritten Devanagari word sample image database of 100 Indian town names.
Abstract: This article presents our recent study on fusion of information at feature and classifier output levels for improved performance of offline handwritten Devanagari word recognition. We consider here two state-of-the-art features, viz., Directional Distance Distribution (DDD) and Gradient-Structural-Concavity (GSC) features along with multi-class SVM classifiers. Here, we study various combinations of DDD features along with one or more features from the GSC feature set. We experiment by presenting different combined feature vectors as input to SVM classifiers. Also, the output vectors of different SVM classifiers fed with different feature vectors are combined by another SVM classifier. The combination of the outputs of two SVMs each being fed with a different feature vector provides superior performance to the performance of a single SVM classifier fed with the combined feature vector. Experimental results are obtained on a large handwritten Devanagari word sample image database of 100 Indian town names. The recognition results on its test samples show that SVM recognition output of DDD features combined with the SVM output of GSC features improves the final recognition accuracy significantly.
15 citations
Cites background from "Handwritten Numeral Databases of In..."
...Recently, a few works on offline images of handwritten isolated Devanagari numeral/character recognition were carried out [4, 5]....
[...]
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...
[...]