Character Recognition: A Neural Network Approach
05 Oct 2012-Iss: 1, pp 17-20
TL;DR: The paper throws light on, one of the application of Neural Network (NN) i.e. Character Recognition, the fundamentals of character recognition, available techniques and emphasis on more recently used technique, neural networks.
Abstract: OCR is the acronym for Optical Character Recognition. This technology allows a machine to automatically recognize characters through as optical mechanism. Human Beings “recognize” many objects in this manner; our eyes are the “optical mechanism.” But while the brain “sees” the input, the ability to comprehend these signals varies in each person according to many factors. In same manner “characters” which are nothing but the images made by the different combinations of lines and curves are also optically recognized by our brain. By reviewing these variables, the challenges faced by the technologist developing an OCR system. Character recognition techniques help in recognizing the characters written on paper documents and converting it in digital form. So Character recognition is gaining interest and importance in the modern world. While the area of character recognition is vast we focus on the fundamentals of character recognition, available techniques and emphasis on more recently used technique, neural networks. The paper throws light on, one of the application of Neural Network (NN) i.e. Character Recognition.
Citations
More filters
TL;DR: The Ant-miner algorithm (AMA) is used for offline OCR of hand written Oriya scripts, popularly known as Utkal lipi, using a rule-based approach and a character recognition tool has been developed using Matlab for observation and validation.
Abstract: Optical Character Recognition (OCR) is one of the challenging areas in the domain of image processing, where the handwritten or printed characters are digitized by using an optical scanner. The image is then analyzed broadly by two methods – (i) matrix space analysis method and (ii) feature space analysis method. Matrix space analysis method takes more memory space and time, compared to feature space analysis. However, it works fine for the scripts in which the strokes are prominent, e.g. English numeric scripts. On the other hand, the feature analysis method is useful where the scripts are complex and having more similarity between the letters in its writing style. Hence, the feature analysis approach is more useful to many of the regional languages. In this paper, we have used the Ant-miner algorithm (AMA) for offline OCR of hand written Oriya scripts, popularly known as Utkal lipi. The AMA is a rule-based approach. The rules are incrementally tuned during the training. The Oriya language contains more than 50 distinct characters i.e. 12 Swara-varnas (i.e., vowels) and 38 Byanjan-varnas (i.e., consonants) and their composite characters. In this work, for the analysis, we define three types of ‘block’s as per the writing styles of the scripts. AMA is then tested with four characters from each ‘block’. Finally, a character recognition tool has been developed using Matlab for observation and validation. General terms: Ant miner algorithm, Optical character recognition (OCR), Oriya character pattern matching
10 citations
Cites methods from "Character Recognition: A Neural Net..."
...To automate the process of learning the computer system is assisted with the technologies such as neural network based approach [1], where the pattern of the individual scripts are saved in the neural network weights [2]....
[...]
03 Mar 2016
TL;DR: A near combination algorithm are developed for each process for the purpose of segmentation and zoning phenomena to achieve better accuracy and to overcome all the drawbacks found in all other available OCR algorithm.
Abstract: Hand written character recognition is the phenomena of enabling a machine to automatically recognize the characters or scripts written in user language. Optical character recognition has become one of the most successful applicants of technology in the field of pattern recognition and artificial intelligence in this project a scanned image is translated into machine established text by means of using optical character recognition. Here a hand written English cursive word is scanned and this image is fed into the computer in which it is recognized using neural network and converted into the same work in equivalent printed characters. A near combination algorithm are developed for each process for the purpose of segmentation and zoning phenomena to achieve better accuracy and to overcome all the drawbacks found in all other available OCR algorithm.
4 citations
01 Jan 2013
TL;DR: An OCR system for 3185 training samples and 13650 testing samples is presented for multi-font English texts and experiments have shown that wavelet features produce better recognition rates 96% than DCT features 92%.
Abstract: Optical Character Recognition (OCR) is a type of computer software designed to translate images of handwritten or typewritten text (usually captured by a scanner or a camera) into machineeditable text by recognizing characters at high speeds one at a time. OCR began as a field of research in pattern recognition, artificial intelligence and machine vision. It is becoming more and more important in the modern world according to economic reasons and business requirements. It helps humans ease their jobs and solve more complex problems by eliminating the time-consuming spent by human operators to re-type the documents and reduce error-prone processes. The presence of any type of noise or a combination of them can severely degrade the performance of OCR system. Though, a number of preprocessing techniques are considered in the present work in order to improve the obtained accuracy of the recognized text. An OCR system for 3185 training samples and 13650 testing samples is presented for multi-font English texts. Experiments have shown that wavelet features produce better recognition rates 96% than DCT features 92%. An improvement overall recognition rates (about 3%) are obtained after classifying characters according to the proportion of Height to Width feature to produce 99% for wavelet and 95% for DCT.
3 citations
17 Oct 2019
TL;DR: A novel algorithm is proposed which considers input from a text file containing Gujarati script and segments words and characters and is validated with 10 numbers written in words and implemented using MATLAB.
Abstract: From past decades, many research works have been carried out for identifying characters from images in Gujarati language. However, a few solutions are available for segmentation of words and characters in Gujarati language from a text file. In this paper, we propose a novel algorithm which considers input from a text file containing Gujarati script and segments words and characters. The proposed algorithm has been validated with 10 numbers written in words, each with varying length, implemented using MATLAB. The screenshots are attached with this paper, which shows segmentation of words and characters. This system is considered as a subsystem of a much bigger system, where Gujarati text is to be converted into to its equivalent speech. Without proper segmentation of words and characters, it is not possible to achieve the intended task. Prior to this, existing solutions and tools are analysed and the summary is presented in the literature survey. Based on the limitations found through the survey, the proposed research work is designed. An experiment is also carried out and discussed in detail in this paper along with the results achieved. At end, conclusion and possible future enhancements are also presented.
2 citations
References
More filters
TL;DR: The objective of this review paper is to summarize and compare some of the well-known methods used in various stages of a pattern recognition system and identify research topics and applications which are at the forefront of this exciting and challenging field.
Abstract: The primary goal of pattern recognition is supervised or unsupervised classification. Among the various frameworks in which pattern recognition has been traditionally formulated, the statistical approach has been most intensively studied and used in practice. More recently, neural network techniques and methods imported from statistical learning theory have been receiving increasing attention. The design of a recognition system requires careful attention to the following issues: definition of pattern classes, sensing environment, pattern representation, feature extraction and selection, cluster analysis, classifier design and learning, selection of training and test samples, and performance evaluation. In spite of almost 50 years of research and development in this field, the general problem of recognizing complex patterns with arbitrary orientation, location, and scale remains unsolved. New and emerging applications, such as data mining, web searching, retrieval of multimedia data, face recognition, and cursive handwriting recognition, require robust and efficient pattern recognition techniques. The objective of this review paper is to summarize and compare some of the well-known methods used in various stages of a pattern recognition system and identify research topics and applications which are at the forefront of this exciting and challenging field.
6,527 citations
TL;DR: Introduction to statistical pattern recognition and nonlinear discriminant analysis - statistical methods.
Abstract: Introduction to statistical pattern recognition * Estimation * Density estimation * Linear discriminant analysis * Nonlinear discriminant analysis - neural networks * Nonlinear discriminant analysis - statistical methods * Classification trees * Feature selection and extraction * Clustering * Additional topics * Measures of dissimilarity * Parameter estimation * Linear algebra * Data * Probability theory.
2,082 citations
Book•
01 Jan 1989TL;DR: In this paper, the authors combine the theoretical foundations of intelligent problem-solving with data structures and algorithms needed for its implementation, including logic, rule, object and agent-based architectures, along with example programs written in LISP and PROLOG.
Abstract: From the Publisher:
Combines the theoretical foundations of intelligent problem-solving with he data structures and algorithms needed for its implementation. The book presents logic, rule, object and agent-based architectures, along with example programs written in LISP and PROLOG.
The practical applications of AI have been kept within the context of its broader goal: understanding the patterns of intelligence as it operates in this world of uncertainty, complexity and change.
The introductory and concluding chapters take a new look at the potentials and challenges facing artificial intelligence and cognitive science. An extended treatment of knowledge-based problem-solving is given including model-based and case-based reasoning.
Includes new material on:
Fundamentals of search, inference and knowledge representation
AI algorithms and data structures in LISP and PROLOG Production systems, blackboards, and meta-interpreters including planers, rule-based reasoners, and inheritance systems.
Machine-learning including ID3 with bagging and boosting, explanation based learning, PAC learning, and other forms of induction
Neural networks, including perceptrons, back propogation, Kohonen networks, Hopfield networks, Grossberg learning, and counterpropagation. Emergent and social methods of learning and adaptation, including genetic algorithms, genetic programming and artificial life.
Object and agent-based problem solving and other forms of advanced knowledge representation
1,166 citations
TL;DR: A feature recognition network for pattern recognition that learns the patterns by remembering their different segments by using a Boolean net algorithm that was developed during past research.
Abstract: Presents a feature recognition network for pattern recognition that learns the patterns by remembering their different segments. The base algorithm for this network is a Boolean net algorithm that the authors developed during past research. Simulation results show that the network can recognize patterns after significant noise, deformation, translation and even scaling. The network is compared to existing popular networks used for the same purpose, especially the Neocognitron. The network is also analyzed as regards to interconnection complexity and information storage/retrieval. >
90 citations
Journal Article•
7 citations