PFID: Pittsburgh fast-food image dataset

Mei Chen, Kapil Dhingra, Wen Wu, Lei Yang, Rahul Sukthankar, Jie Yang
2009 2009 16th IEEE International Conference on Image Processing (ICIP)  
We introduce the first visual dataset of fast foods with a total of 4,545 still images, 606 stereo pairs, 303 360 0 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
more » ... ark 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.
doi:10.1109/icip.2009.5413511 dblp:conf/icip/ChenDWYSY09 fatcat:kwczxwzsrnfw3eqp6vcdgemi6e