Component-Based Representation in Automated Face Recognition
| Autor: | Anil K. Jain, Kathryn Bonnen, Brendan Klare |
|---|---|
| Rok vydání: | 2013 |
| Předmět: |
Face hallucination
Computer Networks and Communications Local binary patterns Computer science business.industry Feature extraction ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Pattern recognition Facial recognition system Component (UML) Active shape model Three-dimensional face recognition Computer vision Artificial intelligence Safety Risk Reliability and Quality Face detection business |
| Zdroj: | IEEE Transactions on Information Forensics and Security. 8:239-253 |
| ISSN: | 1556-6021 1556-6013 |
| DOI: | 10.1109/tifs.2012.2226580 |
| Popis: | This paper presents a framework for component-based face alignment and representation that demonstrates improvements in matching performance over the more common holistic approach to face alignment and representation. This work is motivated by recent evidence from the cognitive science community demonstrating the efficacy of component-based facial representations. The component-based framework presented in this paper consists of the following major steps: 1) landmark extraction using Active Shape Models (ASM), 2) alignment and cropping of components using Procrustes Analysis, 3) representation of components with Multiscale Local Binary Patterns (MLBP), 4) per-component measurement of facial similarity, and 5) fusion of per-component similarities. We demonstrate on three public datasets and an operational dataset consisting of face images of 8000 subjects, that the proposed component-based representation provides higher recognition accuracies over holistic-based representations. Additionally, we show that the proposed component-based representations: 1) are more robust to changes in facial pose, and 2) improve recognition accuracy on occluded face images in forensic scenarios. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|