Large pose invariant face recognition using feature-based recurrent neural network
- Resource Type
- Conference
- Authors
- Salan, Teddy; Iftekharuddin, Khan M.
- Source
- The 2012 International Joint Conference on Neural Networks (IJCNN) Neural Networks (IJCNN), The 2012 International Joint Conference on. :1-7 Jun, 2012
- Subject
- Computing and Processing
Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Face
Face recognition
Vectors
Standards
Feature extraction
Principal component analysis
Training
Large pose invariant face recogniton
Cellular Simulataneous Neural Network
Motion unit
Face Recogntion Vendor Test
Face Recognition Technology (FERET) program
- Language
- ISSN
- 2161-4393
2161-4407
Cellular Simultaneous Recurrent Network (CSRN) is a novel bio-inspired recurrent neural network that mimics reinforcement learning in the brain. CSRN has been proven to be a powerful tool for learning and predicting temporal information in face image sequences. In this work, we propose a novel implementation of feature-based CSRN for large-scale pose invariant face recognition. We also report systematic evaluation and performance comparison of our feature-based CSRN method with other well-known standard algorithms (PCA, LDA, Bayesian Classifier and EBGM) using face recognition technology standards for large-scale pose invariant face recognition.