Open AccessPosted Content
Handwritten Arabic Numeral Recognition using a Multi Layer Perceptron
Reads0
Chats0
TLDR
A feature set of 88 features is designed to represent samples of handwritten Arabic numerals designed to include 72 shadow and 16 octant features and can be extended to include OCR of handwritten characters of Arabic alphabet.Abstract:
Handwritten numeral recognition is in general a benchmark problem of Pattern Recognition and Artificial Intelligence Compared to the problem of printed numeral recognition, the problem of handwritten numeral recognition is compounded due to variations in shapes and sizes of handwritten characters Considering all these, the problem of handwritten numeral recognition is addressed under the present work in respect to handwritten Arabic numerals Arabic is spoken throughout the Arab World and the fifth most popular language in the world slightly before Portuguese and Bengali For the present work, we have developed a feature set of 88 features is designed to represent samples of handwritten Arabic numerals for this work It includes 72 shadow and 16 octant features A Multi Layer Perceptron (MLP) based classifier is used here for recognition handwritten Arabic digits represented with the said feature set On experimentation with a database of 3000 samples, the technique yields an average recognition rate of 9493% evaluated after three-fold cross validation of results It is useful for applications related to OCR of handwritten Arabic Digit and can also be extended to include OCR of handwritten characters of Arabic alphabetread more
Citations
More filters
Offline Urdu Numeral Recognition Using Non-Negative Matrix Factorization
TL;DR: A novel approach of Non-negative Matrix Factorization (NMF) for Urdu handwritten character recognition has been proposed in this research and is proposed to address the problem of handwritten offline numerals.
Book ChapterDOI
An Automatic Annotation Scheme for Scene Text Archival Applications
TL;DR: A novel scheme for automatic generation of annotations by OCRing scene text images is presented and the performance is demonstrated on a smart infobase, a knowledge base designed with trie data structure.
TA : Pengambilan Fitur Angka Jawa Menggunakan Shadow Feature Extraction
TL;DR: Karakter angka Jawa terdiri dari beberapa angka dasar dari angka 0-9, while Metode shadow feature extraction digunakan untuk mengenali ciri dari citra tulisan tangan sebelum nantinya diklasifikasikan jenis karakternya oleh MLP.
Handwritten character recognition usingnaïve bayesclassifier method for desktop and mobile application
S Priyanthy,H. M. M. Naleer +1 more
TL;DR: The results indicate that the proposed system is very effective and yields good recognition rate for character images obtained by camera and applies Bayesian networks classifier to classify the whole image of words.
Journal ArticleDOI
Huruf: An Application for Arabic Handwritten Character Recognition Using Deep Learning
M. Kamal,Fairuz Shaiara,Chowdhury Mohammad Abdullah,Shabbir Ahmed,Tasnim Ahmed,Md. Hasanul Kabir +5 more
TL;DR: In this article , the authors proposed a lightweight convolutional neural network based architecture for recognizing Arabic characters and digits, which consists of a total 18 layers containing four layers each for convolution, pooling, batch normalization, dropout, and finally one Global average pooling and a dense layer.
References
More filters
Book
Neural Networks: A Comprehensive Foundation
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.
Journal ArticleDOI
Online and off-line handwriting recognition: a comprehensive survey
TL;DR: The nature of handwritten language, how it is transduced into electronic data, and the basic concepts behind written language recognition algorithms are described.
Journal ArticleDOI
Off-line Arabic character recognition: the state of the art
TL;DR: In this article, the authors present the state of Arabic character recognition research throughout the last two decades and present the main objective of this paper is to present the current state of the research.
Book ChapterDOI
Recognition of Bangla Handwritten Characters Using an MLP Classifier Based on Stroke Features
TL;DR: A moderately large database of Bangla handwritten character images is used for the recognition purpose and an MLP classifier is trained using a variant of the backpropagation algorithm that uses self-adaptive learning rates.
Journal ArticleDOI
Off-line handwritten Chinese character recognition as a compound Bayes decision problem
Pak-Kwong Wong,Chorkiri Chan +1 more
TL;DR: A handwritten Chinese character off-line recognizer based on contextual vector quantization (CVQ) of every pixel of an unknown character image has been constructed and the CVQ-based language model is the most effective one upgrading the recognition rate by 10.4 percent on the average.
Related Papers (5)
Off-line Handwritten Numeral Recognition using Hybrid Feature Set – A Comparative Analysis
Savita Ahlawat,Rahul Rishi +1 more