Proceedings ArticleDOI
On recognition of Bengali numerals with backpropagation learning
S. Datta,S. Chaudhury,G. Parthasarathy +2 more
- pp 94-99
TLDR
The experiments presented have established the superiority of the MLP and MAXNET combined over the standard MLP classifier and the classical nearest neighbor classifier.Abstract:
The authors address various aspects of the problems associated with processing and recognition of printed and handwritten Bengali numerals. A scheme has been proposed for recognizing handwritten as well as printed numerals with different fonts and writing styles. The scheme was successfully used for the recognition of samples of handwritten numerals and the font from printed numerals with a high degree of accuracy. The scheme was also extended for noisy and occluded numerals. The standard multilayer perceptron (MLP) augmented with MAXNET was used as a classifier. The experiments presented have established the superiority of the MLP and MAXNET combined over the standard MLP classifier and the classical nearest neighbor classifier. >read more
Citations
More filters
A survey on script segmentation for Bangla OCR
TL;DR: The most important and useful properties, advantages, disadvantages of various Bangla scripts, especially the printed scripts are depicted and some ideas regarding the prospective field of Bangla OCR and its applications are given.
Journal ArticleDOI
Bangla Character Recognition for Android Devices
TL;DR: The main target of the project was to build an Android application that can extract text from any image that contains Bengali characters and convert it into an editable document.
Optical character recognition for Bangla documents using HMM
Md. Sheemam Monjel,Mumit Khan +1 more
TL;DR: An OCR program made for Bangla documents that uses HMM for the recognition process and some features of Bangla characters are defined and their extraction process is described.
Book ChapterDOI
Bengali Printed Character Recognition – A New Approach
TL;DR: This paper presents a new method for Bengali character recognition based on view-based approach and proposes a layer-based methodology in modification of the basic view- based processing that facilitates handling of unequal logical partitions.
Journal Article
Shape Representation and Recognition of Bangla Characters using Fourier Descriptor
TL;DR: K-nearest neighbor classifier is used to recognize the characters and the accuracy is 98.4% for training set while it is 89.3% for a test set.
References
More filters
Journal ArticleDOI
An introduction to computing with neural nets
TL;DR: This paper provides an introduction to the field of artificial neural nets by reviewing six important neural net models that can be used for pattern classification and exploring how some existing classification and clustering algorithms can be performed using simple neuron-like components.
Journal ArticleDOI
Fourier Descriptors for Plane Closed Curves
Charles T. Zahn,Ralph Roskies +1 more
TL;DR: It is established that the Fourier series expansion is optimal and unique with respect to obtaining coefficients insensitive to starting point and the amplitudes are pure form invariants as well as are certain simple functions of phase angles.
Journal ArticleDOI
Character recognition—a review
V. K. Govindan,A P Shivaprasad +1 more
TL;DR: There still is a great gap between human reading and machine reading capabilities, and a great amount of further effort is required to narrow-down this gap, if not bridge it.
Journal ArticleDOI
Handwritten numerical recognition based on multiple algorithms
F. Kimura,Malayappan Shridhar +1 more
TL;DR: The authors combine two algorithms for application to the recognition of unconstrained isolated handwritten numerals utilizing features derived from the profile of the character in a structural configuration to recognize the numerals.
Journal ArticleDOI
Classification of Partial 2-D Shapes Using Fourier Descriptors
C. C. Lin,Rama Chellappa +1 more
TL;DR: Experiments with synthetic and real boundaries show that estimates closer to the true values of Fourier descriptors of complete boundaries are obtained and classification experiments performed using real boundaries indicate that reasonable classification accuracies are obtained even when 20-30 percent of the data is missing.