A Novel Biologically Inspired Visual Cognition Model: Automatic Extraction of Semantics, Formation of Integrated Concepts, and Reselection Features for Ambiguity
Peijie Yin2; Hong Qiao1; Wei Wu1; Lu Qi1; Yinlin Li1; Shanlin Zhong1; Bo Zhang2
2017-09
发表期刊IEEE Transactions on Cognitive and Developmental Systems
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
学科领域模式识别与智能系统
DOI10.1109/TCDS.2017.2749978
引用统计
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/21731
专题复杂系统管理与控制国家重点实验室_机器人理论与应用
通讯作者Hong Qiao
作者单位1.中科院自动化所复杂系统管理与控制国家重点实验室
2.中国科学院数学与系统科学研究院
推荐引用方式
GB/T 7714
Peijie Yin,Hong Qiao,Wei Wu,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,2017,10(2):420-431.
APA Peijie Yin.,Hong Qiao.,Wei Wu.,Lu Qi.,Yinlin Li.,...&Bo Zhang.(2017).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 Peijie Yin,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(2017):420-431.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
TCDS2017.pdf(3887KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Peijie Yin]的文章
[Hong Qiao]的文章
[Wei Wu]的文章
百度学术
百度学术中相似的文章
[Peijie Yin]的文章
[Hong Qiao]的文章
[Wei Wu]的文章
必应学术
必应学术中相似的文章
[Peijie Yin]的文章
[Hong Qiao]的文章
[Wei Wu]的文章
相关权益政策
暂无数据
收藏/分享
文件名: TCDS2017.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。