A Novel Biologically Inspired Visual Cognition Model: Automatic Extraction of Semantics, Formation of Integrated Concepts, and Reselection Features for Ambiguity

doi:10.1109/TCDS.2017.2749978

CSpace > 应用数学研究所

	A Novel Biologically Inspired Visual Cognition Model: Automatic Extraction of Semantics, Formation of Integrated Concepts, and Reselection Features for Ambiguity
	Yin, Peijie 1,2; Qiao, Hong 2,3,4; Wu, Wei 3,5; Qi, Lu 3; Li, Yinlin 3; Zhong, Shanlin 2,3; Zhang, Bo1,2,6
	2018-06-01
发表期刊	IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS
ISSN	2379-8920
卷号	10 期号:2 页码:420-431
摘要	Techniques that integrate neuroscience and information science benefit both fields. Many related models have been proposed in computer vision; however, in general, the robustness and recognition precision are still key problems in object recognition models. In this paper, inspired by the process by which humans recognize objects and its biological mechanisms, a new integrated and dynamic framework is proposed that mimics the semantic extraction, concept formation and feature reselection found in human visual processing. The main contributions of the proposed model are as follows: 1) semantic feature extraction: local semantic features are learned from episodic features extracted from raw images using a deep neural network; 2) integrated concept formation: concepts are formed using the local semantic information and structural information is learned through a network; and 3) feature reselection: when ambiguity is detected during the recognition process, distinctive features based on the differences between the ambiguous candidates are reselected for recognition. Experimental results on four datasets show that-compared with other methods-the new proposed model is more robust and achieves higher precision for visual recognition, especially when the input samples are semantically ambiguous. Meanwhile, the introduced biological mechanisms further strengthen the interaction between neuroscience and information science.
关键词	Biologically inspired model object recognition semantic learning structural learning
DOI	10.1109/TCDS.2017.2749978
语种	英语
资助项目	National Science Foundation of China[61210009] ; Strategic Priority Research Program of the CAS[XDB02080003] ; National Key Research and Development Plan of China[2016YFC0300801] ; National Natural Science Foundation of China[61210009] ; National Natural Science Foundation of China[61627808] ; National Natural Science Foundation of China[91648205] ; Development of Science and Technology of Guangdong Province Special Fund Project[2016B090910001]
WOS研究方向	Computer Science ; Robotics ; Neurosciences & Neurology
WOS类目	Computer Science, Artificial Intelligence ; Robotics ; Neurosciences
WOS记录号	WOS:000435198600025
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计
文献类型	期刊论文
条目标识符	http://ir.amss.ac.cn/handle/2S8OKBNM/30521
专题	应用数学研究所
通讯作者	Qiao, Hong
作者单位	1.Chinese Acad Sci, Acad Math & Syst Sci, Inst Appl Math, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 3.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 4.CAS Ctr Excellence Brain Sci & Intelligence Techn, Shanghai 200031, Peoples R China 5.Beijing Key Lab Res & Applicat Robot Intelligence, Beijing 100190, Peoples R China 6.Chinese Acad Sci, Cloud Comp Ctr, Dongguan 523808, Peoples R China
推荐引用方式 GB/T 7714	Yin, Peijie,Qiao, Hong,Wu, Wei,et al. A Novel Biologically Inspired Visual Cognition Model: Automatic Extraction of Semantics, Formation of Integrated Concepts, and Reselection Features for Ambiguity[J]. IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS,2018,10(2):420-431.
APA	Yin, Peijie.,Qiao, Hong.,Wu, Wei.,Qi, Lu.,Li, Yinlin.,...&Zhang, Bo.(2018).A Novel Biologically Inspired Visual Cognition Model: Automatic Extraction of Semantics, Formation of Integrated Concepts, and Reselection Features for Ambiguity.IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS,10(2),420-431.
MLA	Yin, Peijie,et al."A Novel Biologically Inspired Visual Cognition Model: Automatic Extraction of Semantics, Formation of Integrated Concepts, and Reselection Features for Ambiguity".IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS 10.2(2018):420-431.