Feature Learning for Image Classification via Multiobjective Genetic Programming

doi:10.1109/TNNLS.2013.2293418

OPT OpenIR > 光谱成像技术研究室

	Feature Learning for Image Classification via Multiobjective Genetic Programming
	Shao, Ling 1,2; Liu, Li 2; Li, Xuelong3
作者部门	光学影像学习与分析中心
	2014-07-01
发表期刊	IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
ISSN	2162-237X
卷号	25 期号:7 页码:1359-1371
摘要	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.
文章类型	Article
关键词	Feature Extraction Genetic Programming (Gp) Image Classification Multiobjective Optimization
WOS标题词	Science & Technology ; Technology
DOI	10.1109/TNNLS.2013.2293418
收录类别	SCI ; EI
关键词[WOS]	OBJECT RECOGNITION ; FEATURE-EXTRACTION ; SCENE ; RETRIEVAL ; CONTEXT ; CORTEX ; SHAPE
语种	英语
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Hardware & Architecture ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS记录号	WOS:000337906300010
引用统计	被引频次：217[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.opt.ac.cn/handle/181661/22385
专题	光谱成像技术研究室
作者单位	1.Nanjing Univ Informat Sci & Technol, Coll Elect & Informat Engn, Nanjing 210044, Jiangsu, Peoples R China 2.Univ Sheffield, Dept Elect & Elect Engn, Sheffield S1 3JD, S Yorkshire, England 3.Chinese Acad Sci, Xian Inst Opt & Precis Mech, State Key Lab Transient Opt & Photon, Ctr OPT IMagery Anal & Learning, Xian 710119, Peoples R China
推荐引用方式 GB/T 7714	Shao, Ling,Liu, Li,Li, Xuelong. Feature Learning for Image Classification via Multiobjective Genetic Programming[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2014,25(7):1359-1371.
APA	Shao, Ling,Liu, Li,&Li, Xuelong.(2014).Feature Learning for Image Classification via Multiobjective Genetic Programming.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,25(7),1359-1371.
MLA	Shao, Ling,et al."Feature Learning for Image Classification via Multiobjective Genetic Programming".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 25.7(2014):1359-1371.

条目包含的文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Feature Learning for（4134KB）	期刊论文	出版稿	限制开放	CC BY	请求全文