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 principle point of this task is to plan a master framework for, "HCR(English) utilizing Neural Network".
Abstract: In this paper, an endeavor is made to perceive handwritten characters for English letters in order. The principle point of this task is to plan a master framework for, \"HCR(English) utilizing Neural Network\". that can viably perceive a specific character of type design utilizing the Artificial Neural Network approach. The handwritten character acknowledgment issue has become the most well-known issue in AI. Handwritten character acknowledgment has been a difficult space of examination, with the execution of Machine Learning we propose a Neural Network based methodology. Acknowledgment, precision rate, execution and execution time are a significant model that will be met by the technique being utilized.
1 citations
Journal Article•
TL;DR: The objective of the proposed work aims at designing and developing a recognition algorithm for multilingual handwritten numerals through data collection and preprocessing which involves creation of handwritten numeral databases, data collection, round off mean aspect ratio value based representation and identification of features using partial derivatives.
Abstract: The multi-font and multi-lingual handwritten numerals recognition has been a demanding requirement in this decade. This research work proposes multi-lingual handwritten numerals recognition using partial derivatives for classifying handwritten numerals of five major Indian languages. The objective of the proposed work aims at designing and developing a recognition algorithm for multilingual handwritten numerals. This objective is achieved through data collection and preprocessing which involves creation of handwritten numeral databases, data collection, round off mean aspect ratio value based representation and identification of features using partial derivatives. The features derived from partial derivatives are stored in a five dimensional column vector which yielded a recognition rate of 94.80, 95.89, 96.44, 95.81 and 92.03%, respectively for Kannada, Gurumukhi, Sindhi, Malayalam and Tamil Handwritten Numerals respectively.
1 citations
29 Mar 2019
TL;DR: A useful survey on both feature-based and deep learning based domains on popular foreign and Indian scripts concludes that deep learning methods could be more useful as compared to feature based methods.
Abstract: Script identification is an essential task especially in India because of existence of 13 different scripts for writing 22 languages. Major applications of script identification are document sorting, automatic translation, selecting of OCR (Optical Character Recognition) and text area identification. Traditionally, researchers have used feature based methods for script identification but it can be automated through deep learning techniques to reduce comprehensive time. Moreover, CNN (Convolutional Neural Network) based deep learning approaches are less explored for script identification problem. Intention behind this survey on script identification is to make researchers more perceived about the usefulness of deep learning techniques and more specifically, the significance of CNN to deal with script identification problem. This paper contains a useful survey on both feature-based and deep learning based domains on popular foreign and Indian scripts. We have shown comparative analysis between both domains which clearly concludes that deep learning methods could be more useful as compared to feature based methods. In addition, limitations and usefulness of CNN based best practices are also presented.
1 citations
Cites background from "Handwritten Numeral Databases of In..."
...Neural Network(NN) Multilayer Perceptron (MLP) [12] [13] [14] Bayesian Network Probabilistic 4....
[...]
...At last, fully connected layers are used which connect all neurons in one layer to all neurons in another layer, similar to MLP. IV....
[...]
01 Jan 2016
TL;DR: The classifier combination approach to Devanagari character recognition is applied and various fixed combining rules like sum, max, min, product, median and majority voting are used and out of these product rule performs best in most of the cases.
Abstract: In this paper we have applied the classifier combination approach to Devanagari character recognition. Two types of combination models are experimented in this work. The first is based on stacking and the second one is based on parallel combination of classifiers. The chain code and gradient based features are used in this work. Three classifiers namely Linear Discriminent, Quadratic Discriminent and k-nearest neighbor classifier are combined using same features in stacking based approach. In parallel combination three different feature sets namely chain code, gradient based and distance based features are used for the classifiers of similar kind. Various fixed combining rules like sum, max, min, product, median and majority voting are used in both the combination schemes and out of these product rule performs best in most of the cases.
1 citations
01 Jan 2021
TL;DR: A two-stage handwritten numeral recognition system for three most popular scripts used in Indian subcontinent—Devanagari, Bangla and Roman is introduced and is found to be better than some previous approaches.
Abstract: Although various methods have been proposed by the researchers over the years to carry out isolated handwritten numeral recognition, this is still considered as a challenging research problem. The primary challenge occurs because of sizable differences in writing styles of the digit patterns. Literature reveals that several feature extraction and classification methods have been researched upon to optimize the said recognition system but there is still room for improvement. Here, we introduce a two-stage handwritten numeral recognition system for three most popular scripts used in Indian subcontinent—Devanagari, Bangla and Roman. Initially, the global features that are estimated based on Histogram of Oriented Gradients (HOG) feature descriptor help in the formation of inter-numeral groups having nearly similar structure. Then, the optimal subset of features is selected using Genetic Algorithm (GA) on the combination of HOG and local distance features. These optimal features, thus produced, are employed for the classification of handwritten digits within the intra-numeral groups. Finally, the Multi-layer Perceptron (MLP) classifier is used to recognize the numerals. The strength of the present approach is efficient feature selection and the comprehensive classification scheme due to which notable recognition accuracies have been attained which are found to be better than some previous approaches.
1 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...
[...]