Abstract
A face recognition system has been developed and demonstrated at the Rutgers University Center for Computer Aids for Industrial Productivity (CAIP).The system uses a preliminary data reduction step, gray scale projections, anda fast transform technique to greatly reduce the computational complexity ofthe problem and, consequently, the cost of highspeed implementation. Thedecision function is a new, extremely cost-effective neural network, the Mammone/Sankar Neural Tree Network (NTN). This paper examines the use of grayscale projections in detail, and demonstrates the use of 1-dimensional signal processing techniques in 2-dimensional imaging applications. Results are presentedresults showing immunity to changes in expression and small rotations aboutthe vertical axis.
Original language | English (US) |
---|---|
Pages (from-to) | 22-32 |
Number of pages | 11 |
Journal | Proceedings of SPIE - The International Society for Optical Engineering |
Volume | 2277 |
DOIs | |
State | Published - Oct 25 1994 |
Event | Automatic Systems for the Identification and Inspection of Humans 1994 - San Diego, United States Duration: Jul 24 1994 → Jul 29 1994 |
All Science Journal Classification (ASJC) codes
- Electronic, Optical and Magnetic Materials
- Condensed Matter Physics
- Computer Science Applications
- Applied Mathematics
- Electrical and Electronic Engineering