Algorithms For An Integrated Vision-Based Home Security System
This thesis delves into the algorithmic design of two security systems - face recognition system and human motion detection system. The novelty of this scheme is twofold. First, we have developed an eigenedge technique, which employs Principal Component Analysis (PCA) characterisation on the face ed...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Published: |
2005
|
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | This thesis delves into the algorithmic design of two security systems - face recognition system and human motion detection system. The novelty of this scheme is twofold. First, we have developed an eigenedge technique, which employs Principal Component Analysis (PCA) characterisation on the face edge map derived from a novel fuzzy-based Gaussian-like edge detector. Secondly, a three-tier cascaded classification structure has been developed to enable reclassification using different features or classifiers to improve recognition rate, while maintaining efficiency and computational cost at an acceptable level. |
|---|