Title
PFID: Pittsburgh fast-food image dataset
Abstract
We introduce the first visual dataset of fast foods with a total of 4,545 still images, 606 stereo pairs, 303 3600 videos for structure from motion, and 27 privacy-preserving videos of eating events of volunteers. This work was motivated by research on fast food recognition for dietary assessment. The data was collected by obtaining three instances of 101 foods from 11 popular fast food chains, and capturing images and videos in both restaurant conditions and a controlled lab setting. We benchmark the dataset using two standard approaches, color histogram and bag of SIFT features in conjunction with a discriminative classifier. Our dataset and the benchmarks are designed to stimulate research in this area and will be released freely to the research community.
Year
DOI
Venue
2009
10.1109/ICIP.2009.5413511
ICIP
Keywords
Field
DocType
popular fast food chain,sift feature,video signal processing,image capturing,dietary assessment,pittsburgh fast-food image dataset,motion structure,data privacy,pattern classification,discriminative classifier,controlled lab setting,fast food,fast food recognition,object detection,object recognition,computer vision,visual dataset,stereo image processing,color histogram,video privacy-preserving,food image dataset,fast food chains,research community,image motion analysis,structure from motion,indexing terms,histograms,accuracy,visualization
Structure from motion,Scale-invariant feature transform,Object detection,Histogram,Computer vision,Pattern recognition,Color histogram,Computer science,Visualization,Artificial intelligence,Discriminative model,Cognitive neuroscience of visual object recognition
Conference
ISSN
ISBN
Citations 
1522-4880 E-ISBN : 978-1-4244-5655-0
978-1-4244-5655-0
72
PageRank 
References 
Authors
3.20
9
6
Name
Order
Citations
PageRank
Mei Chen119410.92
Kapil Dhingra2723.20
Wen Wu351747.40
Lei Yang4723.20
Rahul Sukthankar56137365.45
Jie Yang62856270.24