Character Recognition Research Research Articles

Application and analysis of machine learning in handwritten digit recognition

It appears from the information that Character recognition research is currently focused on handwritten digit recognition, a significant subfield of optical character recognition, i.e. the use of computers to recognise and process digital information. In today's increasingly mainstream computer and data era, handwritten numeric recognition can simplify the process of paper-based offices, reduce the intensity of work when analysing data statistics afterwards and improve work efficiency. There are many algorithms to achieve recognition, each with different recognition accuracy, implementation efficiency and application scope. Based on the basic concepts described above, this thesis investigates the efficiency and accuracy of three algorithms - template matching, SVM and deep learning - in recognising handwritten digits with different sample sizes. The models or kernel functions currently used to process data of varying complexity and restricted scenarios also require continuous improvement to ensure accuracy, making it all the more important to discuss them in detail.

A Review of the Current Status of AI Research in Handwritten Chinese Character Recognition

With the continuous development of artificial intelligence technology, there have been attempts to utilize AI in the field of linguistics. In this context, research and development in AI-based Chinese character recognition technology has spanned 40 years, with its outcomes attracting significant attention. However, in the field of Chinese character recognition, the research into offline handwritten recognition technology is particularly challenging due to the unique characteristics of handwritten Chinese characters. The main issue in current research is the significant decrease in accuracy for characters composed of similar components or characters with similar overall shapes. The focus of research solutions has been on modern mechanical programming and other engineering aspects, while research that integrates the inherent characteristics of Chinese characters themselves has been relatively overlooked. The author believes that combining engineering technology research with a deeper understanding of the nature of Chinese characters can solve many of the current problems. This paper reviews the current state of related domestic and international research to identify areas with significant potential for improvement and progress in research, and finally proposes directions for future research.

Automatic Numeral Recognition System Using Local Statistical and Geometrical Features

Optical Character Recognition (OCR) research includes computer vision, artificial intelligence, and pattern recognition. Character recognition has garnered a lot of attention in the last decade due to its broad variety of uses and applications, including multiple-choice test data, business documents (e.g., ID cards, bank notes, passports, etc.), and automatic number plate recognition. This paper introduces an automatic recognition system for printed numerals. The automatic reading system is based on extracting local statistical and geometrical features from the text image. Those features are represented by eight vectors extracted from each digit. Two of these features are local statistical (A, A th), and six are local geometrical (P1, P2, P3, P4, P5, and P6). Thus, the database created consists of 1120 statistical and geometrical features. For the purpose of recognition, the features of the test image are compared with the features of all the images saved in the database depending on the value of the Minimum Distance (MD). All digits (0–9) were identified with 100% accuracy. The average computational time required to recognize a numeral at any font size is 0.06879 seconds.

Tangut Character Stroke Detection with Improved Hough Transform

In the research of Tangut character recognition, it was attempted to detect the stroke of character with standard Hough transform (SHT), but hindered by the inability of SHT to detect the curve-line. In this paper, Hough transform with guidance of endpoints (HTGE) was proposed to achieve better performance on the aspect of curve and short line detection. HTGE is implemented based on the conception of hypothesis and verification, first, to assume there is line between each pair of endpoints, and then the existence of line is checked according to the corresponding area accumulated value in the parameter domain. With setting up of test object and evaluation criterion, the experiment was carried out to determine the key parameter for the best performance, and it can be concluded from the experiment result that considerable performance can be achieved with HTGE in the application of line detection.

A Holistic Approach to Urdu Language Word Recognition using Deep Neural Networks

Urdu is one of the most popular languages in the world. It is a Persianized standard register of the Hindi language with considerable and valuable literature. While digital libraries are constantly replacing conventional libraries, a vast amount of Urdu literature is still handwritten. Digitizing this handwritten literature is essential to preserve it and make it more accessible. Nevertheless, the scarcity of Urdu Optical Character Recognition (OCR) research limits a digital library's scope to a manual document search. The limited research work in this area is mainly due to the complexity of Urdu Script. Unlike the English language, the Urdu writing style is cursive, bidirectional, and character shapes and sizes highly vary depending on their position. Holistic word recognition is found to be a better solution among many other text segmentation techniques as it takes the complete word into account instead of segmenting it explicitly or implicitly. For this project, the data of five different Urdu words were collected for training and testing a convolutional neural network and 96% recognition accuracy was achieved.

Intelligent Handwritten Character Recognition For Malayalam Scripts Using Deep Learning Approach

Machine Learning, especially Deep Learning has been incorporated into Pattern Recognition and Image Processing for the Handwritten Character Recognition (HCR) research which is always a hot area of research. Foreign scripts are enriched with Handwritten Character Recognition (HCR) studies. But very less research can be seen for HCR in Indian scenario, especially in Malayalam script. This paper provides an overview of different feature extraction and classification techniques used for Handwritten Character Recognition of Malayalam Scripts using Deep Learning Approaches. The accuracy measures of classification of the different algorithms have been given so that the researchers can select a particular algorithm with high performance.

Research on the Preprocessing of Tai Le Character Recognition

Tai Le character is a kind of alphabetic writing with a long history, and its character recognition research plays an important role in inheriting and protecting Tai Le. Preprocessing is an key part of the Tai Le character recognition system, the quality of the preprocessing directly affects the recognition rate in the recognition system. Image preprocessing is the premise of feature extraction and recognition, since the directly input image usually contains noise, it affects the recognition effect. Therefore, it is of great application value and far-reaching historical significance to study the preprocessing technology of Tai Le character recognition. This paper proposes the image preprocessing method of Tai Le character, including graying, binarization, de-noise, and edge detection, and achieves good preprocessing results, which lays a foundation for feature extraction and recognition of Tai Le character.

A Solution for Line Segmentation Problems in Sindhi Character Recognition System

The Sindhi language uses extended and modified set of the Arabic and Persian alphabets. It is the largest extension of the Arabic alphabet. Thus, Arabic or any other Arabic script based language character recognition system cannot recognize all characters of Sindhi. From character recognition point of view, Sindhi is a tough script. Sindhi’s cursive, context-sensitive characteristics, a large set of characters, highly similar shapes of the basic character, font-type variations, and size variations create high challenges for Sindhi character recognition research. In addition, line segmentation is a hard task as we have non-uniformity in the line heights. In this paper, we present an algorithm for segmenting the Sindhi text image into lines. The proposed algorithm solves the over-segmentation and under-segmentation problems in the line segmentation for Sindhi documents. The algorithm is tested on 100 text images of different Sindhi books and it has successfully segmented 99.95% lines correctly.

A survey of mono- and multi-lingual character recognition using deep and shallow architectures: indic and non-indic scripts

The cultural and regional diversity across the world and specifically in India has given birth to a large number of writing systems and scripts having a variety of character sets. For scripts having a larger character set, just a simple keyboard with limited character set is not the optimal way for providing inputs to the computer. Variations in individual handwriting due to mood swings, changes in medium of writing, changes in writing styles, etc. pose a challenge before the character recognition (CR) research community. Similar kinds of symbols in various scripts and languages act as a big barrier in multilingual CR. Lack of benchmark results and corpora for multilingual CR hinder the research in multilingual CR. There have been only a limited number of articles for optimal combination of features and classifiers to process multilingual data. Multilingual CR has least explored the Indic scripts. This paper presents a detailed review and analysis of the work done in multilingual online as well as offline CR for Indic and non-Indic scripts. The paper mainly contributes in two ways: Firstly, it provides a clear perspective about various phases of monolingual and multilingual CR; and secondly, identifies the major deficiencies in monolingual and multilingual CR for printed and handwritten text. It contributes by giving an in-depth view of work done at each phase including data acquisition, pre-processing, segmentation, feature extraction, recognition and post-processing of CR. Issues to be resolved at each phase have also been elaborated. The recent work done using Deep and Shallow architectures has been analysed. Tools used for these architectures have been compared to highlight their pros and cons. The present work also suggests how further research can be conducted in the field of monolingual and multilingual CR. The problems such as CR in hybrid documents, identifying more reliable features, resolving issues of similar characters, identifying optimal combination strategies for deep and shallow architectures, etc. need to be tackled in future research.

Synthesis of Common Arabic Handwritings to Aid Optical Character Recognition Research

Document analysis tasks such as pattern recognition, word spotting or segmentation, require comprehensive databases for training and validation. Not only variations in writing style but also the used list of words is of importance in the case that training samples should reflect the input of a specific area of application. However, generation of training samples is expensive in the sense of manpower and time, particularly if complete text pages including complex ground truth are required. This is why there is a lack of such databases, especially for Arabic, the second most popular language. However, Arabic handwriting recognition involves different preprocessing, segmentation and recognition methods. Each requires particular ground truth or samples to enable optimal training and validation, which are often not covered by the currently available databases. To overcome this issue, we propose a system that synthesizes Arabic handwritten words and text pages and generates corresponding detailed ground truth. We use these syntheses to validate a new, segmentation based system that recognizes handwritten Arabic words. We found that a modification of an Active Shape Model based character classifiers—that we proposed earlier—improves the word recognition accuracy. Further improvements are achieved, by using a vocabulary of the 50,000 most common Arabic words for error correction.

Telugu Handwritten Isolated Characters Recognition using Two Dimensional Fast Fourier Transform and Support Vector Machine

Research in character recognition is an old application in the area of pattern recognition and has attracted many researchers during the last few decades. Handwritten character recognition (HCR) is of two types namely, Online and Offline. The recognition accuracy for HCR is less than 60% as per the literature survey. Also the non existence of standard database for Indian languages is another reason for motivation of this work. This work describes Offline HCR by extracting features using 2D FFT and using the support vector machines for Telugu documents. The best percentage recognition accuracy for Telugu handwritten characters is 71%.

Development of Nepali Character Database for Character Recognition based on Clustering

dataset to apply recognition algorithms and generate efficient models out of them. In case of Nepali language, no such character dataset exists for character recognition research, at least in the public domain. Nepali language has 36 consonant characters, 12 vowels character and each vowel character can modify each consonant characters. In this regard, there can be total of 446 characters including Nepali numeric characters. So, manually creating dataset for Nepali characters requires tons of effort, cost and time. In this paper, an elegant way of creating Nepali character dataset using semi-supervised clustering approach is described which minimizes effort and time. Also, optimization is done on existing segmentation algorithm [1] to segment Nepali characters for both handwritten and scanned Nepali text. Complex features are extracted from these segmented characters by applying Discrete Cosine Transform and Wavelet transform. Thus, these extracted features are used to create database of Nepali characters using phash and k-means cluster. Presently, the database contains 38,493 characters distributed among 52 different clusters.

Efficient Feature Extraction Techniques for Offline Handwritten Gurmukhi Character Recognition

As a result of advances in optical character recognition research, several techniques for handwritten character recognition have surfaced. These techniques require good quality features as their input for the recognition process. In this paper, we have proposed two different feature extraction techniques, namely, parabola curve fitting based features and power curve fitting based features for offline handwritten Gurmukhi character recognition. In order to assess the quality of features in offline handwritten Gurmukhi character recognition, we have also analyzed the performance of other recently proposed feature extraction techniques, namely, zoning, diagonal, directional, transition, intersection and open end points, gradient and chain code features. Each technique has been tested by using 3,500 images of offline handwritten Gurmukhi characters. Support vector machine (SVM) and k-NN classifiers have been used to recognize the characters in this work. The proposed system achieves a recognition accuracy of 98.10 and 97.14 % using k-NN and SVM classifiers, respectively, when power curve fitting based features are used as input to the classification process.

The Research of Character Recognition Based on Improved Complexity Index Feature Extraction Algorithm

The Research of Character Recognition Based on Improved Complexity Index Feature Extraction Algorithm

The MNIST Database of Handwritten Digit Images for Machine Learning Research [Best of the Web

In this issue, “Best of the Web” presents the modified National Institute of Standards and Technology (MNIST) resources, consisting of a collection of handwritten digit images used extensively in optical character recognition and machine learning research.

Survey and Analysis of Devnagari Character Recognition Techniques using Neural Networks

ABSTRACT English Character Recognition techniques have been studied extensively in the last few years and its progress and success rate is quite high. But for regional languages these are still emerging and their success rate is moderate. There are millions of people who speak Hindi and use Devnagari script for writing. As digital documentation in Devnagari script is gaining popularity. Research in Optical Character Recognition (OCR) is very essential especially with an eye on its applications in banks, post offices, defense organizations, library automation, etc. Devnagari Optical Character Recognition needs more attention as it is national language and there is less development in this field due to complexity in the script. This paper describes the current techniques being used for DOCR. The overview of the system is explained with the available techniques and their current status. Keywords Devnagari Character Recognition, Off-line Handwriting Recognition, Segmentation, Feature Extraction, OCR.

Handwritten Character Recognition Research Based on Adaptive Minimum Distance Classifiers Integration

It is difficulty to gain completely satisfactory effect if a single classification is used to check a complicated recognition classification problem. Using the complementarities between the different classify method, integrating many classifiers, it can reduce the identification mistake and strengthen recognition robustness. Taking a offline handwritten number recognition system as an example, adopting Bayesian discriminate function based on minimal mistake rate, uniting recognition algorithm of RBF kernel function, using Bagging technology, adaptive minimum distance classifiers integration is designed in which there is minimal mistake rate. Furthermore, an offline handwritten number recognition system in high accuracy is exploited in which there is adaptive and self-learning function. It can be used for important economic fields such as financial statement and bank paper.

Modified region decomposition method and optimal depth decision tree in the recognition of non-uniform sized characters – An experimentation with Kannada characters

In contrast to English alphabets, some characters in Indian languages such as Kannada, Hindi, Telugu may have either horizontal or vertical or both the extensions making it difficult to enclose every such character in a standard rectangular grid as done quite often in character recognition research. In this work, an improved method is proposed for the recognition of such characters (especially Kannada characters), which can have spread in vertical and horizontal directions. The method uses a standard sized rectangle which can circumscribe standard sized characters. This rectangle can be interpreted as a two-dimensional, 3×3 structure of nine parts which we define as bricks. This structure is also interpreted as consecutively placed three row structures of three bricks each or adjacently placed three column structures of three bricks each.It is obvious that non-uniform sized characters cannot be contained within the standard rectangle of nine bricks. The work presented here proposes to take up such cases. If the character has horizontal extension, then the rectangle is extended horizontally by adding one column structure of three bricks at a time, until the character is encapsulated. Likewise, for vertically extended characters, one row structure is added at a time. For the characters which are smaller than the standard rectangle, one column structure is removed at a time till the character fits in the shrunk rectangle. Thus, the character is enclosed in a rectangular structure of m×n bricks where m⩾3 and n⩾1. The recognition is carried out intelligently by examining certain selected bricks only instead of all mn bricks. The recognition is done based on an optimal depth logical decision tree developed during the Learning phase and does not require any mathematical computation.

Machine-printed character recognition revisited: re-application of recent advances in handwritten character recognition research

The increasing automation of document processing applications has emphasised the need for robust and reliable recognition of machine-printed characters. Although research in character recognition is now focused principally on applications in reading handwritten characters, this paper demonstrates how recent progress in the area of multiple-expert classification can be exploited to provide new approaches to the processing of printed data. Established classification algorithms have been used in a new multiple-expert framework to generate an optimised decision combination platform comprising multiple experts, and significant improvements in overall recognition performance on machine-printed characters have been achieved.

Off-line Arabic character recognition: the state of the art

Machine simulation of human reading has been the subject of intensive research for almost three decades. A large number of research papers and reports have already been published on Latin, Chinese and Japanese characters. However, little work has been conducted on the automatic recognition of Arabic characters because of the complexity of printed and handwritten text, and this problem is still an open research field. The main objective of this paper is to present the state of Arabic character recognition research throughout the last two decades.