Genetic Programming with Image-RelatedOperators and A Flexible Program Structure forFeature Learning in Image Classification.pdf (2.37 MB)

Genetic Programming with Image-Related Operators and A Flexible Program Structure for Feature Learning in Image Classification

Download (2.37 MB)
journal contribution
posted on 29.10.2020, 01:05 by Ying Bi, Bing Xue, Mengjie Zhang
IEEE Feature extraction is essential for solving image classification by transforming low-level pixel values into high-level features. However, extracting effective features from images is challenging due to high variations across images in scale, rotation, illumination, and background. Existing methods often have a fixed model complexity and require domain expertise. Genetic programming with a flexible representation can find the best solution without the use of domain knowledge. This paper proposes a new genetic programming-based approach to automatically learning informative features for different image classification tasks. In the new approach, a number of image-related operators, including filters, pooling operators and feature extraction methods, are employed as functions. A flexible program structure is developed to integrate different functions and terminals into a single tree/solution. The new approach can evolve solutions of variable depths to extract various numbers and types of features from the images. The new approach is examined on 12 different image classification tasks of varying difficulty and compared with a large number of effective algorithms. The results show that the new approach achieves better classification performance than most benchmark methods. The analysis of the evolved programs/solutions and the visualisation of the learned features provide deep insights on the proposed approach.

History

Preferred citation

Bi, Y., Xue, B. & Zhang, M. (2020). Genetic Programming with Image-Related Operators and A Flexible Program Structure for Feature Learning in Image Classification. IEEE Transactions on Evolutionary Computation, PP(99), 1-1. https://doi.org/10.1109/TEVC.2020.3002229

Journal title

IEEE Transactions on Evolutionary Computation

Volume

PP

Issue

99

Publication date

01/01/2020

Pagination

1-1

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Publication status

Published

ISSN

1089-778X

eISSN

1941-0026

Exports