Research Article
FaceDate: A Mobile Cloud Computing App for People Matching
@INPROCEEDINGS{10.4108/eai.15-12-2016.2267654, author={Pradyumna Neog and Hillol Debnath and Jianchen Shan and Nafize Paiker and Narain Gehani and Reza Curtmola and Xiaoning Ding and Cristian Borcea}, title={FaceDate: A Mobile Cloud Computing App for People Matching}, proceedings={11th International Conference on Body Area Networks}, publisher={ACM}, proceedings_a={BODYNETS}, year={2017}, month={4}, keywords={mobile cloud app face matching}, doi={10.4108/eai.15-12-2016.2267654} }- Pradyumna Neog
Hillol Debnath
Jianchen Shan
Nafize Paiker
Narain Gehani
Reza Curtmola
Xiaoning Ding
Cristian Borcea
Year: 2017
FaceDate: A Mobile Cloud Computing App for People Matching
BODYNETS
EAI
DOI: 10.4108/eai.15-12-2016.2267654
Abstract
This paper presents FaceDate, a novel mobile app that matches persons based on their facial looks. Each FaceDate user uploads their profile face photo and trains the app with photos of faces they like. Upon user request, FaceDate detects other users located in the proximity of the requester and performs face matching in real-time. If a mutual match is found, the two users are notified and given the option to start communicating. FaceDate is implemented over our Moitree middleware for mobile distributed computing assisted by the cloud. The app is designed to scale with the number of users, as face recognition is done in parallel at different users. FaceDate can be configured for (i) higher performance, in which case the face recognition is done in the cloud or (ii) higher privacy, in which case the face recognition is done on the mobiles. The experimental results with Android-based phones demonstrate that FaceDate achieves promising performance.
