Font Size: a A A

Design And Development Of A Bio-Identification Prototype System Based On Face Recognition

Posted on:2006-07-08Degree:MasterType:Thesis
Country:ChinaCandidate:H B SunFull Text:PDF
GTID:2168360152975613Subject:Mechanical design and theory
Abstract/Summary:PDF Full Text Request
Biometric technologies are becoming the foundation of an extensive array of highly secure identification and personal verification solutions. Among the features measured, facial feature identification and verification are gaining popularity and diverse applications for the reason that they are considered to be non-invasive, low cost, and natural biometric technologies.This thesis deals with the technologies related to facial identification and presents a Bio-identification prototype system based on face recognition. The main contents of the thesis are listed as followings:1. Functional module and workflow of the system are achieved based on the requirement and functional analysis of the system, as well as the technical solution of the system. A Bio-identification prototype system is developed based on face recognition, which realizes many functions including identification retrieval, enrollment, real-time face detection, eyeballs location and management of face image database et al. Then, the performance of the system is proved by a series of tests.2. Special image-preprocessing technologies for face recognition are studied such as geometric normalization and photometric normalization, as well as their effects on recognition rate. Accordingly an optimal image-preprocessing technology for the system is adapted.3. Concepts of rectangle features and "integral image" are introduced. And based on the basic principle of Adaboost algorithm and rectangle features, the cascade classfiers for face detection and eyes location is constructed. Finally, the performance of the classifers is tested.4. With the comparison between various algorithms of face recognition synthetically, the algorithm based on PCA+LDA is chosen as the technical solution of the system's face recognition module. According to the principle of this algorithm, the classfier for face recognition is constructed. Finally, the performace of this classfier is tested.
Keywords/Search Tags:face recognition, Bio-identification, image preprocessing, face detection, eyeballs location, Adaboost, linear discriminant analysis
PDF Full Text Request
Related items