FAME: Face association through model evolution

Date
2015-06
Advisor
Instructor
Source Title
IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Print ISSN
Electronic ISSN
Publisher
IEEE
Volume
Issue
Pages
43 - 49
Language
English
Type
Conference Paper
Journal Title
Journal ISSN
Volume Title
Abstract

We attack the problem of building classifiers for public faces from web images collected through querying a name. The search results are very noisy even after face detection, with several irrelevant faces corresponding to other people. Moreover, the photographs are taken in the wild with large variety in poses and expressions. We propose a novel method, Face Association through Model Evolution (FAME), that is able to prune the data in an iterative way, for the models associated to a name to evolve. The idea is based on capturing discriminative and representative properties of each instance and eliminating the outliers. The final models are used to classify faces on novel datasets with different characteristics. On benchmark datasets, our results are comparable to or better than the state-of-the-art studies for the task of face identification. © 2015 IEEE.

Course
Other identifiers
Book Title
Keywords
Accuracy, Buildings, Computational modeling, Data models, Face, Noise measurement, Training, Buildings, Classification (of information), Data structures, Face recognition, Iterative methods, Pattern recognition, Personnel training, Accuracy, Benchmark datasets, Computational model, Face, Face identification, Model evolution, Noise measurements, State of the art, Computer vision
Citation
Published Version (Please cite this version)