06256412.pdf (1.36 MB)

Extracting image features for classification by two-tier genetic programming

Download (1.36 MB)
conference contribution
posted on 27.10.2020, 21:41 by Harith Al-Sahaf, A Song, K Neshatian, Mengjie Zhang
Image classification is a complex but important task especially in the areas of machine vision and image analysis such as remote sensing and face recognition. One of the challenges in image classification is finding an optimal set of features for a particular task because the choice of features has direct impact on the classification performance. However the goodness of a feature is highly problem dependent and often domain knowledge is required. To address these issues we introduce a Genetic Programming (GP) based image classification method, Two-Tier GP, which directly operates on raw pixels rather than features. The first tier in a classifier is for automatically defining features based on raw image input, while the second tier makes decision. Compared to conventional feature based image classification methods, Two-Tier GP achieved better accuracies on a range of different tasks. Furthermore by using the features defined by the first tier of these Two-Tier GP classifiers, conventional classification methods obtained higher accuracies than classifying on manually designed features. Analysis on evolved Two-Tier image classifiers shows that there are genuine features captured in the programs and the mechanism of achieving high accuracy can be revealed. The Two-Tier GP method has clear advantages in image classification, such as high accuracy, good interpretability and the removal of explicit feature extraction process. © 2012 IEEE.

History

Preferred citation

Al-Sahaf, H., Song, A., Neshatian, K. & Zhang, M. (2012, January). Extracting image features for classification by two-tier genetic programming. In Proceedings of 2012 IEEE Congress on Evolutionary Computation 2012 IEEE Congress on Evolutionary Computation (CEC), Brisbane, QLD, Australia (1 pp. 567-574). IEEE Press. https://doi.org/10.1109/CEC.2012.6256412

Conference name

2012 IEEE Congress on Evolutionary Computation (CEC)

Conference Place

Brisbane, QLD, Australia

Conference start date

10/06/2012

Conference finish date

15/06/2012

Title of proceedings

Proceedings of 2012 IEEE Congress on Evolutionary Computation

Volume

1

Series

IEEE Congress on Evolutionary Computation

Contribution type

Published Paper

Publication or Presentation Year

01/01/2012

Pagination

567-574

Publisher

IEEE Press

Publication status

Published

ISSN

1089-778X

Exports