Variogram-based feature extraction for neural network recognition of logos

Tuan D Pham

doi:10.1117/12.477399

Back

Conference proceeding

Variogram-based feature extraction for neural network recognition of logos

Tuan D Pham

Proceedings of SPIE, Vol.5015(1), pp.22-29

Applications of Artificial Neural Networks in Image Processing VIII

27/03/2003

DOI: https://doi.org/10.1117/12.477399

Abstract

This paper presents a new approach for extracting spatial features of images based on the theory of regionalized variables. These features can be effectively used for automatic recognition of logo images using neural networks. Experimental results on a public-domain logo database show the effectiveness of the proposed approach.

Metrics

3 Record Views

Details

Title: Variogram-based feature extraction for neural network recognition of logos
Creators - without role: Tuan D Pham - Defence Science and Technology Group
Publication Details: Proceedings of SPIE, Vol.5015(1), pp.22-29
Conference: Applications of Artificial Neural Networks in Image Processing VIII
Identifiers: 9925137708331
Academic Unit: Prince Mohammad Bin Fahd University
Language: English
Resource Type: Conference proceeding