Neural Based Binarization Techniques

Authors:
Hatem HAMZA;Abdel BELAID;Eddie SMIGIEL
Affiliations:
LORTA. University Nancy 2;LORTA. University Nancy 2;LICIA-INSA de Strasbourg
Venue:
ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
Year:
2005

Citing 3
Cited 0

Self-organizing maps

Self-organizing maps
An Introduction to Digital Image Processing

An Introduction to Digital Image Processing
Serialized Unsupervised Classifier for Adaptative Color Image Segmentation: Application to Digitized Ancient Manuscripts

ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 1 - Volume 01

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper introduces three neural based binarization techniques. These techniques start with a Self Organizing Map (SOW applied on the image to extract its most representative grey levels or colors. The classiJication goes further in two different ways. In the case of grey level images, the Kmeans algorithm or Sauvola 's or Niblack S thresholds are used, whereas a Multi Layer Perceptron (MLP) is used in the case of color images. The obtained results are discussed and we show that they are better than those of some classical binarization techniques.