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: This study is going to focus on the Off-Line English language characters in order to extract geometric moment’s features for the Characters shape of the Handwriting recognition to reduce the similarity error for intra-class (of the same character), with the increase of the similarityerror for inter- class (of different characters) in recognition of Off- line handwritten English characters with Fuzzy logic.
Abstract: Recognition rate of handwritten English character is still limited due to presence of large variation of shape, scale and format in hand written characters. The thing that's very difficult to deal with in character recognition is that the handwriting of a person differs from one person to another and considering the human error it is impossible for one person to write the same thing over and over again where it has to be the exact writing. However this is considered individualistic where the consistent individual features are hidden in the character handwriting. For that reason this study going to focus on the Off-Line English language characters in order to extract geometric moment’s features for the Characters shape of the Handwriting recognition. The geometric moment’s features are being completed thoroughly also the presence of solo features will be legitimized by checking and investigating it granularly; therefore the idea of applying the Invariant Discretization. By injecting the solo performance to the system through the injection of different issues for the solo feature into individual feature or standard performance this is being accomplished by the support of Invariant Discretization. Where the advantage of the Invariant Discretization to reduce the similarity error for intra-class (of the same character), with the increase of the similarity error for inter-class (of different characters)in recognition of Off-Line handwritten English characters with Fuzzy logic .
1 citations
Cites background from "Handwritten Numeral Databases of In..."
...Character recognition is nothing but Machine simulation of human reading [1], [2]....
[...]
Journal Article•
TL;DR: A method of extracting triangle features using triangle geometry based on the dominant of distribution foreground for digit recognition has been proposed and comparison results classification of accuracies demonstrated the effectiveness of the proposed method.
Abstract: Digit recognition has been studied for four decades ago. Many approaches and techniques such as Hidden Markov Model, Neural Network, back-propagation and k-nearest neighbor have been applied to recognize the digit images. Recently, the triangle geometry method has been applied to extract features from triangle properties such as ratio, angle and gradient. However, a problem in determining points of a triangle was triggered due to the points’ position in straight line. Thus, a method of extracting triangle features using triangle geometry based on the dominant of distribution foreground for digit recognition has been proposed. The dominant of distribution foreground is referred to the digit of ‘0’ which is represented as a foreground image during the binarization process. The process to determine the triangle points are based on the dominant of distribution foreground. The classifiers of Support Vector Machine (SVM) and Multi-Layer Perceptron (MLP) are used to measure the classification accuracies for four types of digit datasets which are HODA, IFCHDB, MNIST, and BANGLA. The comparison results classification of accuracies demonstrated the effectiveness of our proposed method.
1 citations
Cites methods from "Handwritten Numeral Databases of In..."
...For BANGLA dataset, it was developed by Pattern Recognition Unit and Vision Computer, Institute of Indian Statistic....
[...]
...In feature extraction stage, all generated triangle features were used and the grid search using libSVM method was used to obtain the best cost and gamma for digit datasets of HODA, IFCHDB, MNIST, and BANGLA....
[...]
...The classifiers of Support Vector Machine (SVM) and Multi-Layer Perceptron (MLP) are used to measure the classification accuracies for four types of digit datasets which are HODA, IFCHDB, MNIST, and BANGLA....
[...]
...For BANGLA dataset, the sample of the testing dataset was used is 4,000 while the training dataset is 19,392....
[...]
...Table 1 Results of cost and gamma for each dataset Dataset Cost (c) Gamma (𝜸) IFCHDB 8.0 0.00048828125 HODA 8.0 0.0078125 BANGLA 8.0 0.001953125 MNIST 8.0 0.0078125 66 e-ISSN: 2289-8131 Vol. 10 No. 2-7 Table 2 Comparison results of classification accuracies (...
[...]
TL;DR: In this paper, a Semi-Supervised Generative Adversarial Network (SGAN) was applied to generate Bangla handwritten numerals and it successfully generated Bangla digits.
Abstract: Handwritten digit or numeral recognition is one of the classical issues in the area of pattern recognition and has seen tremendous advancement because of the recent wide availability of computing resources. Plentiful works have already done on English, Arabic, Chinese, Japanese handwritten script. Some work on Bangla also have been done but there is space for development. From that angle, in this paper, an architecture has been implemented which achieved the validation accuracy of 99.44% on BHAND dataset and outperforms Alexnet and Inception V3 architecture. Beside digit recognition, digit generation is another field which has recently caught the attention of the researchers though not many works have been done in this field especially on Bangla. In this paper, a Semi-Supervised Generative Adversarial Network or SGAN has been applied to generate Bangla handwritten numerals and it successfully generated Bangla digits.
TL;DR: MatrriVasha has proposed a dataset that intends to recognize Bangla 120(one hundred twenty) compound characters that consist of 2552(two thousand five hundred fifty-two) isolated handwritten characters written unique writers which were collected from within Bangladesh.
Abstract: At present, recognition of the Bangla handwriting compound character has been an essential issue for many years. In recent years there have been application-based researches in machine learning, and deep learning, which is gained interest, and most notably is handwriting recognition because it has a tremendous application such as Bangla OCR. MatrriVasha, the project which can recognize Bangla, handwritten several compound characters. Currently, compound character recognition is an important topic due to its variant application, and helps to create old forms, and information digitization with reliability. But unfortunately, there is a lack of a comprehensive dataset that can categorize all types of Bangla compound characters. MatrriVasha is an attempt to align compound character, and it's challenging because each person has a unique style of writing shapes. After all, MatrriVasha has proposed a dataset that intends to recognize Bangla 120(one hundred twenty) compound characters that consist of 2552(two thousand five hundred fifty-two) isolated handwritten characters written unique writers which were collected from within Bangladesh. This dataset faced problems in terms of the district, age, and gender-based written related research because the samples were collected that includes a verity of the district, age group, and the equal number of males, and females. As of now, our proposed dataset is so far the most extensive dataset for Bangla compound characters. It is intended to frame the acknowledgment technique for handwritten Bangla compound character. In the future, this dataset will be made publicly available to help to widen the research.
Additional excerpts
...[17]Bhattacharya, Ujjwal & Chaudhuri, Bidyut....
[...]
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...
[...]