Feature Learning for Image Classification Via Multiobjective Genetic Programming

Ling Shao, Li Liu, Xuelong Li

Research output: Contribution to journalArticlepeer-review

205 Citations (Scopus)

Abstract

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.
Original languageEnglish
Pages (from-to)1359-1371
JournalIEEE Transactions on Neural Networks and Learning Systems
Volume25
Issue number7
Early online date12 Dec 2013
DOIs
Publication statusPublished - Jul 2014

Fingerprint

Dive into the research topics of 'Feature Learning for Image Classification Via Multiobjective Genetic Programming'. Together they form a unique fingerprint.

Cite this