Feature Learning for Image Classification Via Multiobjective Genetic Programming

Shao, Ling, Liu, Li and Li, Xuelong (2014) Feature Learning for Image Classification Via Multiobjective Genetic Programming. IEEE Transactions on Neural Networks and Learning Systems, 25 (7). pp. 1359-1371. ISSN 2162-237X

Full text not available from this repository. (Request a copy)
Official URL: http://dx.doi.org/10.1109/TNNLS.2013.2293418


Feature extraction is the first and most critical step in image classification. Most existing image classification methods use hand-crafted features, which are not adaptive for different image domains. In this paper, we develop an evolutionary learning methodology to automatically generate domain-adaptive global feature descriptors for image classification using multiobjective genetic programming (MOGP). In our architecture, a set of primitive 2-D operators are randomly combined to construct feature descriptors through the MOGP evolving and then evaluated by two objective fitness criteria, i.e., the classification error and the tree complexity. After the entire evolution procedure finishes, the best-so-far solution selected by the MOGP is regarded as the (near-)optimal feature descriptor obtained. To evaluate its performance, the proposed approach is systematically tested on the Caltech-101, the MIT urban and nature scene, the CMU PIE, and Jochen Triesch Static Hand Posture II data sets, respectively. Experimental results verify that our method significantly outperforms many state-of-the-art hand-designed features and two feature learning techniques in terms of classification accuracy.

Item Type: Article
Uncontrolled Keywords: Feature extraction, genetic programming (GP), image classification, multiobjective optimization
Subjects: G400 Computer Science
G700 Artificial Intelligence
Department: Faculties > Engineering and Environment > Computer and Information Sciences
Depositing User: Paul Burns
Date Deposited: 10 Jun 2015 12:00
Last Modified: 12 Oct 2019 22:30
URI: http://nrl.northumbria.ac.uk/id/eprint/22817

Actions (login required)

View Item View Item


Downloads per month over past year

View more statistics