IMAGE SEGMENTATION AND RECOGNITION FOR MULTI-CLASS CHINESE FOOD

被引：6

作者：

Liang, Yuxiang ^{[1
]}

Li, Jiangfeng ^{[1
]}

Zhao, Qinpei ^{[1
]}

Rao, Weixiong ^{[1
]}

Zhang, Chenxi ^{[1
]}

Wang, Congrong ^{[2
]}

机构：

[1] Tongji Univ, Sch Software Engn, Shanghai, Peoples R China

[2] Tongji Univ, Dept Endocrinol & Metab, Shanghai Peoples Hosp 4, Sch Med, Shanghai, Peoples R China

来源：

2022 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP | 2022年

基金：

上海市自然科学基金;

关键词：

Food Image Segmentation; Food Recognition; Multi-Class Chinese Food; Deep Learning; CLASSIFICATION;

D O I：

10.1109/ICIP46576.2022.9898001

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

For multi-class food images, an excellent segmentation method has a great influence on accuracy of recognition result, and hence improve the effectiveness of dietary management for diabetics. For Chinese food images, there are some challenges during the processing, such as blurred outlines, rich colors, and varied appearances due to various cooking methods. To overcome these difficulties, we propose a ChineseFoodSeg approach to obtain accurate and efficient multi-class segmentation. A food recognition model, Two-Path Global Local Network (TPGLNet), is also introduced to jointly learn complementary global and local features of the bounding box and the segment. Experiments on the ChineseDiabetesFood187 dataset collected by us demonstrate that the new methods are competitive compared to existing segmentation and recognition methods.

引用

页码：3938 / 3942

页数：5

共 26 条

[1] SLIC Superpixels Compared to State-of-the-Art Superpixel Methods [J].

Achanta, Radhakrishna ;

Shaji, Appu ;

Smith, Kevin ;

Lucchi, Aurelien ;

Fua, Pascal ;

Suesstrunk, Sabine .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2012, 34 (11) :2274-2281

[2]

[Anonymous], 2019, ICML

[3] Benchmarking algorithms for food localization and semantic segmentation [J].

Aslan, Sinem ;

Ciocca, Gianluigi ;

Mazzini, Davide ;

Schettini, Raimondo .

INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS, 2020, 11 (12) :2827-2847

[4] Fabry-Perot fiber-optic immunosensor based on suspended layer-by-layer (chitosan/polystyrene sulfonate) membrane [J].

Chen, L. H. ;

Chan, C. C. ;

Menon, R. ;

Balamurali, P. ;

Wong, W. C. ;

Ang, X. M. ;

Hu, P. B. ;

Shaillender, M. ;

Neu, B. ;

Zu, P. ;

Tou, Z. Q. ;

Poh, C. L. ;

Leong, K. C. .

SENSORS AND ACTUATORS B-CHEMICAL, 2013, 188 :185-192

[5]

Chen Xinyun, 2017, Targeted backdoor attacks on deep learning systems using data poisoning

[6] Food Recognition: A New Dataset, Experiments, and Results [J].

Ciocca, Gianluigi ;

Napoletano, Paolo ;

Schettini, Raimondo .

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2017, 21 (03) :588-598

[7]

Deng J, 2009, PROC CVPR IEEE, P248, DOI 10.1109/CVPRW.2009.5206848

[8] Unsupervised segmentation of color-texture regions in images and video [J].

Deng, YN ;

Manjunath, BS .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2001, 23 (08) :800-810

[9]

He KM, 2020, IEEE T PATTERN ANAL, V42, P386, DOI [10.1109/ICCV.2017.322, 10.1109/TPAMI.2018.2844175]

[10] Deep Residual Learning for Image Recognition [J].

He, Kaiming ;

Zhang, Xiangyu ;

Ren, Shaoqing ;

Sun, Jian .

2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :770-778

← 1 2 3 →