Loading...
Please wait, while we are loading the content...
Similar Documents
Augmenting face recognition with social context
| Content Provider | Indraprastha Institute of Information Technology, Delhi |
|---|---|
| Author | Bhardwaj, Romil |
| Abstract | Face recognition is traditionally based on features extracted from face images which capture various intrinsic characteristics of faces to distinguish between individuals. However, humans do not perform face recognition in isolation and instead utilize a wide variety of contextual cues in order to perform accurate recognition. Social context or co-occurrence of individuals is one such cue that humans utilize to reinforce face recognition output. A social graph can adequately model social-relationships between di fferent individuals and this can be utilized to augment traditional face recognition methods. In this research, we present an evaluative human study on the use of social context by humans to augment face recognition. Motivated by its results, we propose a novel method to generate a social-graph based on a collection of group photographs and learn the social context information. We also propose a novel algorithm to combine results from a commercial face recognition system and social context information to perform face identication. To further leverage information present in the from of image timestamp and geotags, a framework is presented to utilize spatiotemporal information to enhance face recognition. Since no prior human image datasets exist which have geotag and timestamp information embedded, a new spatio-temporal dataset with tagged location and time is presented as an accompaniment to this framework. Experimental results on two publicly available datasets and our dataset show that social and spatio-temporal context information can improve face recognition and help bridge the gap between humans and machines in face recognition. |
| File Format | |
| Language | English |
| Access Restriction | Authorized |
| Subject Keyword | Face Recognition Social Context Social Networks Human Study Graphs Geotags |
| Content Type | Text |
| Educational Degree | Bachelor of Technology (B.Tech.) |
| Subject | Data processing & computer science |
