Holistic cursive word recognition based on perceptual features

Authors:
José Ruiz-Pinales;René Jaime-Rivas;María José Castro-Bleda
Affiliations:
FIMEE - University of Guanajuato, Tampico 912, 36730 Salamanca, Gto., Mexico;FIMEE - University of Guanajuato, Tampico 912, 36730 Salamanca, Gto., Mexico;Departamento de Sistemas Informáticos y Computación, Universidad Politécnica de Valencia, Valencia, Spain
Venue:
Pattern Recognition Letters
Year:
2007

Citing 19
Cited 4

Linear feature detection and enhancement in noisy images via the Radon transform

Pattern Recognition Letters
A survey of the Hough transform

Computer Vision, Graphics, and Image Processing
On the Probabilistic Interpretation of Neural Network Classifiers and Discriminative Training Criteria

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Survey of Methods and Strategies in Character Segmentation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Unconstrained handwriting recognition applied to the processing of bank cheques

Unconstrained handwriting recognition applied to the processing of bank cheques
A Lexicon Driven Approach to Handwritten Word Recognition for Real-Time Applications

IEEE Transactions on Pattern Analysis and Machine Intelligence
Global Word Shape Processing in Off-Line Recognition of Handwriting

IEEE Transactions on Pattern Analysis and Machine Intelligence
Holistic Verification of Handwritten Phrases

IEEE Transactions on Pattern Analysis and Machine Intelligence
Lexicon reduction using key characters in cursive handwritten words

Pattern Recognition Letters - Special issue on pattern recognition in practice VI
Use of the Hough transformation to detect lines and curves in pictures

Communications of the ACM
The Role of Holistic Paradigms in Handwritten Word Recognition

IEEE Transactions on Pattern Analysis and Machine Intelligence
The Handbook of Brain Theory and Neural Networks

The Handbook of Brain Theory and Neural Networks
An Adaptive Approach to Offline Handwritten Word Recognition

IEEE Transactions on Pattern Analysis and Machine Intelligence
Symbolic/neural recognition of cursive amounts on bank cheques

ICDAR '95 Proceedings of the Third International Conference on Document Analysis and Recognition (Volume 1) - Volume 1
Directional Pattern Matching for Character Recognition Revisited

ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 2
Holistic Word Recognition for Handwritten Historical Documents

DIAL '04 Proceedings of the First International Workshop on Document Image Analysis for Libraries (DIAL'04)
Backpropagation applied to handwritten zip code recognition

Neural Computation
Input feature selection for classification problems

IEEE Transactions on Neural Networks
Using mutual information for selecting features in supervised neural net learning

IEEE Transactions on Neural Networks

Improving isolated handwritten word recognition using a specialized classifier for short words

CAEPIA'09 Proceedings of the Current topics in artificial intelligence, and 13th conference on Spanish association for artificial intelligence
Offline handwritten Amharic word recognition

Pattern Recognition Letters
Segment confidence-based binary segmentation (SCBS) for cursive handwritten words

Expert Systems with Applications: An International Journal
Binary segmentation algorithm for English cursive handwriting recognition

Pattern Recognition

Quantified Score

Hi-index	0.10

Visualization

Abstract

This work presents a holistic system for the off-line recognition of cursive words based on the extraction of perceptual features by means of convolution with templates of line segments. The method works directly on gray-level images to avoid losing information due to binarization. Features are represented spatially in order to preserve topological information which is well suited for recognition through convolutional neural networks. Moreover, our feature extraction method does not need to detect baselines to find ascenders and descenders. The system has been tested on small and medium vocabulary sizes demonstrating the feasibility of the proposed method.