Food det: Detecting foods in refrigerator with supervised transformer network

doi:10.1016/j.neucom.2019.10.106

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 图像与视频分析团队

	Food det: Detecting foods in refrigerator with supervised transformer network
	Zhu, Yousong 1,2; Zhao, Xu 1,2; Zhao, Chaoyang 1,2; Wang, Jinqiao 1,2; Lu, Hanqing 1,2
刊名	NEUROCOMPUTING
	2020-02-28
卷号	379 页码:162-171
关键词	Food detection Spatial transformer Object detection
ISSN号	0925-2312
DOI	10.1016/j.neucom.2019.10.106
通讯作者	Zhu, Yousong(yousong.zhu@nlpr.ia.ac.cn)
英文摘要	Most of existing methods mainly focus on the food image recognition which assumes that one food image contains only one food item. However, in this paper, we present a system to detect a diversity of foods in refrigerator where multiple food items may exist. In view of the refrigerator environment, we propose a food detection framework based on the supervised transformer network. More specifically, the supervised transformer network, dotted as RectNet, is first proposed to automatically select the irregular food regions and transform them to the frontal views. Then, based on the rectified food images, we further propose an end-to-end detection network that predicts the categories and locations of food items. The proposed detection network, called Lite Fully Convolutional Network (LiteFCN), is evolved from the advanced object detection algorithm Faster R-CNN while several significant improvements are tailored to achieve a higher accuracy and keep inference time efficiency. To validate the effectiveness of each component of our method, we build a real-world refrigerator dataset with 80 classes. Extensive experiments demonstrate that our methods achieve the state-of-the-art results, which improves the baseline by a large margin, e.g., 3-5% in terms of F-measure. We also show that the proposed detection network achieve a competitive result on the public PASCAL VOC2007 dataset, which outperforms the Faster R-CNN by 2.3% with a higher speed. (C) 2019 Elsevier B.V. All rights reserved.
资助项目	Natural Science Foundation of China[61772527] ; Natural Science Foundation of China[61806200] ; Natural Science Foundation of China[61876086]
WOS关键词	CONTEXT
WOS研究方向	Computer Science
语种	英语
出版者	ELSEVIER
WOS记录号	WOS:000507464700014
资助机构	Natural Science Foundation of China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/29487]
专题	自动化研究所_模式识别国家重点实验室_图像与视频分析团队
通讯作者	Zhu, Yousong
作者单位	1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, 95 Zhongguancun East Rd, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Zhu, Yousong,Zhao, Xu,Zhao, Chaoyang,et al. Food det: Detecting foods in refrigerator with supervised transformer network[J]. NEUROCOMPUTING,2020,379:162-171.
APA	Zhu, Yousong,Zhao, Xu,Zhao, Chaoyang,Wang, Jinqiao,&Lu, Hanqing.(2020).Food det: Detecting foods in refrigerator with supervised transformer network.NEUROCOMPUTING,379,162-171.
MLA	Zhu, Yousong,et al."Food det: Detecting foods in refrigerator with supervised transformer network".NEUROCOMPUTING 379(2020):162-171.