Two-Tier genetic programming: towards raw pixel-based image classification

  • Authors:

  • Harith Al-Sahaf;Andy Song;Kourosh Neshatian;Mengjie Zhang

  • Affiliations:

  • School of Engineering and Computer Science, Victoria University of Wellington, P.O. Box 600, Wellington 6140, New Zealand;School of Computer Science and Information Technology, RMIT University, G.P.O. Box 2476, Melbourne 3001, Australia;School of Engineering and Computer Science, Victoria University of Wellington, P.O. Box 600, Wellington 6140, New Zealand and Department of Computer Science and Software Engineering, University of ...;School of Engineering and Computer Science, Victoria University of Wellington, P.O. Box 600, Wellington 6140, New Zealand

  • Venue:
  • Expert Systems with Applications: An International Journal
  • Year:
  • 2012

Quantified Score

Hi-index 12.05

Visualization

Abstract

Classifying images is of great importance in machine vision and image analysis applications such as object recognition and face detection. Conventional methods build classifiers based on certain types of image features instead of raw pixels because the dimensionality of raw inputs is often too large. Determining an optimal set of features for a particular task is usually the focus of conventional image classification methods. In this study we propose a Genetic Programming (GP) method by which raw images can be directly fed as the classification inputs. It is named as Two-Tier GP as every classifier evolved by it has two tiers, the other for computing features based on raw pixel input, one for making decisions. Relevant features are expected to be self-constructed by GP along the evolutionary process. This method is compared with feature based image classification by GP and another GP method which also aims to automatically extract image features. Four different classification tasks are used in the comparison, and the results show that the highest accuracies are achieved by Two-Tier GP. Further analysis on the evolved solutions reveals that there are genuine features formulated by the evolved solutions which can classify target images accurately.