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 Jan 2019
TL;DR: A novel feature extraction and selection method is proposed for the recognition of isolated handwritten Marathi numbers based on one-dimensional Discrete Cosine Transform (1-D DCT) algorithm for reducing the dimensionality of feature space.
Abstract: Optical character recognition system is hotcake for the researchers since last four decades. Recognition of handwritten Devanagari characters and digits is comparatively a tough task as compared to recognition other scripts like English or Latin. In this manuscript, a novel feature extraction and selection method is proposed for the recognition of isolated handwritten Marathi numbers based on one-dimensional Discrete Cosine Transform (1-D DCT) algorithm for reducing the dimensionality of feature space. The scanned document is preprocessed and segmented to create isolated numerals. Features for each numeral can be calculated after normalizing the numeral image to 32 × 32 size. Based on these reduced features, the numerals are classified into appropriate groups. Database of 6000 numerals size is used for the proposed work. Neural network is used for classification of numerals based on the extracted and selected features. Experimental results show accuracy observed for the method is 90.30%.
4 citations
01 Dec 2020
TL;DR: A non-explicit feature extraction method using a multi-scale multi-column skip convolutional neural network to derive the final feature descriptor encoding a character or digit image.
Abstract: Finding local invariant patterns in handwritten characters and/or digits for optical character recognition is a difficult task. Variations in writing styles from one person to another make this task challenging. We have proposed a non-explicit feature extraction method using a multi-scale multi-column skip convolutional neural network in this work. Local and global features extracted from different layers of the proposed architecture are combined to derive the final feature descriptor encoding a character or digit image. Our method is evaluated on four publicly available datasets of isolated handwritten Bangla characters and digits. Exhaustive comparative analysis against contemporary methods establish the efficacy of our proposed approach. The implementation of our present work can be found at:
https://github.com/DVLP-CMATERJU/Skip-Connected-Multi-column-Network
.
4 citations
TL;DR: A novel feature extraction and selection method is proposed for the recognition of isolated handwritten Marathi numbers which is based on one dimensional Discrete Cosine Transform (DCT) algorithm which gives improved results as compared to zonal DCT and DWT method.
Abstract: Recognition of handwritten Marathi character/digits is comparatively a tough task as compared to English. It has several types of applications including the postal code reading and sorting, banks check amount processing. In this paper a novel feature extraction and selection method is proposed for the recognition of isolated handwritten Marathi numbers which is based on one dimensional Discrete Cosine Transform (DCT) algorithm. The scanned document is pre-processed and segmented to create isolated numerals. Features for each numeral can be calculated after normalizing the numeral image to 32 × 32 size. Based on these reduced features, the numerals are classified into appropriate groups. Neural network is used for classification of numerals based on the extracted features. The results of proposed method are compared with the results obtained using Discrete Wavelet Transform and zonal discrete cosine transform (ZDCT). The proposed approach gives improved results as compared to zonal DCT and DWT method. Experimental results shows accuracy observed for the method is 90.30% with normalized numeral image of size 32 × 32.
4 citations
Cites methods from "Handwritten Numeral Databases of In..."
...In most of the comparison with the Template methods, the normalization of the position and the size of the feature is carried out for comparing the features for matching purpose [13, 14] and the performance of the normalization is very important in order to get remedy from the situation for sampling in advance....
[...]
27 Apr 2019
TL;DR: Several approaches that have used in producing the triangle geometry features in various object recognition such as fingerprint, face, digit, biometric and vehicle detection are reviewed.
Abstract: The geometrical form such as polygon shape can be used to represent object image via their geometrical properties. The geometry shapes such as polygon including rectangles, squares, pentagons and triangles can be used to produce geometry features through the feature extraction process. The use of geometrical forms in object recognition has been applied in determining similar object images which have broadly used in recognizing digit, biometric and vehicle detection. The triangle shape formation is essential to construct in order to produce triangle features. Otherwise, the triangle features cannot be produced. However, each of object recognition has different approaches to construct triangle shape due to their different characteristics such as style, pattern, shape and type which made the triangle features produced are different. This paper reviews several approaches that have used in producing the triangle geometry features in various object recognition such as fingerprint, face, digit dan vehicle detection. The aspects addressed are triangle shape formation, elements used as the benchmark to generate triangle points and properties or characteristics used as features type.
4 citations
Cites methods from "Handwritten Numeral Databases of In..."
...The author of [13] has applied the triangle shape feature process on four types of digit image such as MNIST [15], HODA [14], BANGLA [16] and IFCHDB [17]....
[...]
Journal Article•
TL;DR: Recognition of Devanagari character consists of Image correction, segmentation and character recognition which uses Eigen space method which uses Gerschgorin's theorem for comparison.
Abstract: Recognition of Devanagari character consists of Image correction, segmentation and character recognition. Image correction digitizes the input characters making it available for further processing. Principle component analysis is used to discover the hidden and unclear part and segmentation separates individual characters to identify each character. The most crucial part of any character recognition system is the process of segmentation as characters are recognized individually. The result of recognition is dependent on the accuracy of segmentation. For extraction and recognition we used Eigen space method which uses Gerschgorin's theorem for comparison. Handwritten Devanagari script is nowadays a popular topic for researchers as less work is done on this topic. Handwritten Devanagari characters are difficult to recognize due to the presence of header line and various modifiers. Recognition of fused characters is also a major concern for researchers as fused character is treated as a single character resulting in an error.
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...
[...]