1. UKM Learning and Research Repository
2. Master Thesis / Tesis Master
3. Faculty of Information Science and Technology / Fakulti Teknologi dan Sains Maklumat

Title:	Finger vein authentication system using neural network
Authors:	Azadeh Noori Hoshyar (P49110)
Supervisor:	Riza Bin Sulaiman, Prof. Dr.
Keywords:	Finger vein Authentication system Neural network Biometric identification
Issue Date:	15-Apr-2011
Description:	Biometrics systems for identification purposes have been developed for decades. Different methods include fingerprint, face, iris, retina, signature, gait, voice, hand vein, hand/finger geometry, DNA information have been proposed while fingerprint, face, iris and signature are considered as traditional ones. Each method has its disadvantages. Fingerprint systems usually have low security because they are left everywhere whenever touching a surface, hence patterns can be counterfeited. Similarly face and voice patterns can easily be cloned. Iris scanning produce a strong light that shine into eyes which make this method uncomfortable. Contrasting with other biometrics, vein patterns which are hidden inside the body, makes the systems highly secure and distinguishable, and they are not been affected by the situation of the outer skin. This study investigated a Smart Access Control using Finger Vein authentication and Neural Network. Fourteen finger vein images collected from individuals by shining a near-infrared light through fingers. Automated image cropping was implemented. Image processing was done for reducing noise of finger vein images. The patterns of veins were extracted by combining two segmentation methods include: (i) Gradient based threshold and morphological operation (ii) Maximum Curvature Points in Image Profiles. After extracting the vein image features, Neural Network was used to get the quality of training and testing. Neural Network was also applied for the purpose of recognizing individuals.,Master/Sarjana
Pages:	76
Call Number:	TK7882.B56.H647 2011
Publisher:	UKM, Bangi
URI:	https://ptsldigital.ukm.my/jspui/handle/123456789/476125
Appears in Collections:	Faculty of Information Science and Technology / Fakulti Teknologi dan Sains Maklumat

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.