Multi-layer Classification Approach for Online Handwritten Gujarati Character Recognition

Naik, Vishal A.; Desai, Apurva A.

doi:10.1007/978-981-13-1135-2_45

Cited by 9 publications

(6 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A number of researchers still believe that SVM performs better than most of the other techniques in classifying the handwritten characters. This is the reason why SVM is still being used for the purpose of classification of characters in HCR [77]- [80].…”

Section: B Kernel Methodsmentioning

confidence: 99%

“…This is the reason why a number of research articles on character recognition of Indian scripts are growing each year. researchers have used techniques like Tesseract OCR and google multilingual OCR [113], Convolutional Neural Network (CNN) [70], [114], Deep Belief Network with the distributed average of gradients feature [188], Modified Neural Network with the aid of elephant herding optimization [189], VGG (Visual Geometry Group) [117] and SVM classifier with the polynomial and linear kernel [80] VIII. RESEARCH TRENDS Characters written by different individuals create large intraclass variability, which makes it difficult for classifiers to perform robustly.…”

Section: F Indian Scriptmentioning

confidence: 99%

See 1 more Smart Citation

Handwritten Optical Character Recognition (OCR): A Comprehensive Systematic Literature Review (SLR)

Memon

Sami

Khan³

et al. 2020

IEEE Access

355

View full text Add to dashboard Cite

Given the ubiquity of handwritten documents in human transactions, Optical Character Recognition (OCR) of documents have invaluable practical worth. Optical character recognition is a science that enables to translate various types of documents or images into analyzable, editable and searchable data. During last decade, researchers have used artificial intelligence / machine learning tools to automatically analyze handwritten and printed documents in order to convert them into electronic format. The objective of this review paper is to summarize research that has been conducted on character recognition of handwritten documents and to provide research directions. In this Systematic Literature Review (SLR) we collected, synthesized and analyzed research articles on the topic of handwritten OCR (and closely related topics) which were published between year 2000 to 2019. We followed widely used electronic databases by following pre-defined review protocol. Articles were searched using keywords, forward reference searching and backward reference searching in order to search all the articles related to the topic. After carefully following study selection process 176 articles were selected for this SLR. This review article serves the purpose of presenting state of the art results and techniques on OCR and also provide research directions by highlighting research gaps.

show abstract

Section: B Kernel Methodsmentioning

confidence: 99%

Section: F Indian Scriptmentioning

confidence: 99%

Handwritten Optical Character Recognition (OCR): A Comprehensive Systematic Literature Review (SLR)

Memon

Sami

Khan³

et al. 2020

IEEE Access

355

View full text Add to dashboard Cite

show abstract

“…The system has obtained an average accuracy of 95.65% using proposed twolayer classification approach and it took an average processing time of 0.095 seconds per stroke. The performance of the proposed system is increased compared to the multilayer classification approach [13]. An average accuracy of 94.13% is obtained using a multilayer system and it took an average processing time of 0.103 seconds per stroke.…”

Section: Classificationmentioning

confidence: 99%

“…The system obtained the highest accuracy of 91.63% using SVM with RBF kernel. In [13] the authors have used multi-layer classification using support vector machine classifier. They have used different kernels in both layers.…”

Section: Introductionmentioning

confidence: 99%

Online Handwritten Gujarati Character Recognition: Two-Layer Classification Approach

Naik¹,

Desai²

2019

IJRAT

Self Cite

View full text Add to dashboard Cite

The Gujarati language has large and complex character set and many characters have similar strokes, which makes OCR more challenging.Here we suggest a two-layer classification technique with SVM (RBF) and k-NN classifiers in order to propose a robust online handwritten character recognition for Gujarati language. In the first layer of classification, SVM classifier with the RBF kernel is used and in the second layer, k-NN classifier is used.The training data of second layer classifier is decided based on the outcome of first layer classifier. Training data of a group of characters which are similar to a character returned by first layer classifier, is supplied to k-NN classifier. A hybrid feature set consisting first and second order derivative of pixel values, zoning, and normalized chain code feature. The data set of around 12000 samples was generated from different writers. Around 2000 samples of data set is used for training and rest of the samples are used to test the system. The proposed system has obtained an average accuracy of 94.65% and an average processing time of 0.095 seconds per stroke.

show abstract

“…Structural features focus on the shape of the character, such as line, points, curve, etc. Geometric also features part of the structural features [17], Transformation-based features belong to Fourier Transform category [18], Zoning [3], projections [19] are the most common statistical features where zoning method is most popular method compare to other methods of this category. Horizontal, vertical, and diagonal, these three types of method can be used to extract the feature based on the zoning method.…”

Section: Literaturementioning

confidence: 99%

Zig-zag diagonal and ANN for English character recognition

Gautam¹

2019

IJATCSE

View full text Add to dashboard Cite

Pattern recognition is the most popular are in the modern world. Significant progress has made in English character and digits recognition technology. However, the performance of the existing system of English character and digits recognition can be increased. This study is suggested a novel method, zig-zag diagonal feature extraction method along with ANN to increase the recognition rate of the English character and digit recognition system. The proposed method of this method is tested on an official dataset of English characters (EMNIST) and English digits (MNIST), achieving a 99.8% accuracy and 94% accuracy, respectively.

show abstract

Multi-layer Classification Approach for Online Handwritten Gujarati Character Recognition

Cited by 9 publications

References 23 publications

Handwritten Optical Character Recognition (OCR): A Comprehensive Systematic Literature Review (SLR)

Handwritten Optical Character Recognition (OCR): A Comprehensive Systematic Literature Review (SLR)

Online Handwritten Gujarati Character Recognition: Two-Layer Classification Approach

Zig-zag diagonal and ANN for English character recognition

Contact Info

Product

Resources

About