Segmenting images with support vector machines

Author

Reyna, Roberto A. ; Hernandez, Neil ; Esteve, Daniel ; Cattoen, Michel

Author_Institution

Lab. d´´Autom. et d´´Anal. des Syst., CNRS, Toulouse, France

Volume

1

fYear

2000

fDate

2000

Firstpage

820

Abstract

The aim of this work is to propose an original image segmentation methodology to detect and localise objects or patterns in an image. This new technology has two parts: (a) the main module is a SVM neural network whose goal is the image segmentation in order to detect and localise objects having regular patterns (represented by a block of pixels), and then, (b) a simple morphological processing, to eliminate isolated misclassified pixels. The importance of this methodology is highlighted with the results obtained in the recognition of 2D symbolic codes. Another advantage of our algorithm is its regularity that may be exploited to propose a parallel hardware architecture

Keywords

image recognition; image segmentation; learning automata; mathematical morphology; neural net architecture; object detection; parallel architectures; pattern recognition; 2D symbolic codes recognition; SVM neural network; image segmentation; isolated misclassified pixels elimination; morphological processing; neural network architecture; object detection; object localisation; parallel hardware architecture; pixels; support vector machines; Application software; Artificial neural networks; Face recognition; Image segmentation; Neural networks; Object detection; Pattern recognition; Pixel; Support vector machine classification; Support vector machines;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing, 2000. Proceedings. 2000 International Conference on

Conference_Location

Vancouver, BC

ISSN

1522-4880

Print_ISBN

0-7803-6297-7

Type

conf

DOI

10.1109/ICIP.2000.901085

Filename

901085