Paper Info
Title
Cooperation of multi-layer perceptrons for the estimation of skew angle in text document images
Abstract
Estimating the skew angle in text document images can be a crucial problem in optical character recognition. Based on a new sensor array processing technique, an original solution to skew angle estimation (SAE) is proposed. Thanks to the reformulation of the SAE problem in the framework of angle of arrival theory, a fast and accurate method is presented that is based on the cooperation of two neural networks. The first neural net is a three-layer perceptron receiving on input the values of the correlation matrix of the signals; the output is a “rough” estimation of the angle to estimate. This gross estimate is then used to initialize the weights of a second multi-layer perceptron (MLP). The second MLP is built in order to perform a maximum likelihood-like optimization, therefore reaching good performances. The system, though trained on simulated radar data, shows good performances on noisy handwritten texts
Year
DOI
Venue
1995
10.1109/ICDAR.1995.602122
Document Analysis and Recognition, 1995., Proceedings of the Third International Conference
Keywords
Field
DocType
array signal processing,document image processing,maximum likelihood estimation,multilayer perceptrons,neural nets,optical character recognition,optimisation,maximum likelihood-like optimization,multilayer perceptrons,neural net,noisy handwritten texts,optical character recognition,sensor array processing technique,simulated radar data,skew angle estimation,text document images,three-layer perceptron
Radar,Pattern recognition,Computer science,Sensor array,Optical character recognition,Angle of arrival,Artificial intelligence,Covariance matrix,Artificial neural network,Perceptron,Text document
Conference
Volume
ISBN
Citations 
2
0-8186-7128-9
10
PageRank 
References 
Authors
1.31
3
2
Name
Order
Citations
PageRank
Rondel, N.1101.31
Gilles Burel2297113.35