| Summary: | 碩士 === 國立暨南國際大學 === 通訊工程研究所 === 97 === With an increasing emphasis on security, personal authentication based on biometrics has been receiving extensive attention over the past decade. Among many different biometric technologies, this thesis examines palm-print technique for personal identification and develops a good performance recognition system based on human hand features. It is implemented and tested on VIP-CC Lab. hand image database. The proposed system includes four modules: image acquisition, image pre-processing, feature extraction, and recognition modules. The system captures a hand image using digital camera, then uses some image processing algorithms to localize the region of the interest of palmprint from the hand image via image pre-processing module. The feature extraction module first adopts Neighboring Gray Level Dependence Matrix (NGLDM) as the discriminating texture features. And then using GLCM for statistical. The system encodes the features to generate its palmprint feature codes. Finally, the system applies these feature codes for palmprint matching in recognition module.
It is implemented and tested on the palmprint image database. The Experimental results show that the system has an encouraging performance on the hand database (including 600 images from 100 classes). In the image preprocessing module, we checked the accuracy of the image subjectively and obtained the success rate of 90.00%. Feature extraction method based on NGLDM and 3D GLCM use the projection to gather statistics of relation between pixel-tuples, and utilize the different feature combination, we attain the recognition rates up to EER = 98.000 % (64 bytes) (according to equal error rate, EER). Even under the circumstance of FAR = 0%, the system still approaches the recognition rates above 90.000% (acceptance of authentic, AA). This thesis analyzes the experiment results to verify the related inferences of the proposed system and provides useful information for further research.
|
|---|
