(For USM Staff/Student Only)

EngLib USM > Ω School of Electrical & Electronic Engineering >

Raspberry pi-based finger vein recognition system using PCANet

Raspberry pi-based finger vein recognition system using PCANet / Quek Ee Wen
Sistem Pengecaman Urat Jari (FVRS) merupakan salah satu teknologi biometrik yang dapat mengecam identiti individu berdasarkan corak urat yang unik. Berbanding dengan biometrik lain, ia merupakan cara yang lebih selamat, anti-pemalsuan dan bersih. Oleh itu, ia berjaya digunakan dalam banyak sistem pengesahan masa kini. FVRS asal hanya menyediakan fungsi pengesahan dan bukannya pengenalpastian. Bagi pengenalpastian, proses pemprosesan imej melibatkan process pemprosesan imej, pengekstrakan ciri-ciri dan klasifikasi. Projek ini menggunakan proses pra pemprosesan seperti pengesanan kelebihan, pembetulan orientasi dan pengekstrakan kaisan kepentingan (ROI) yang telah dibangunkan sebelum ini. Objektif utama dalam projek ini adalah melaksanakan teknik pengekstrakan ciri-ciri yang dapat memaksimumkan prestasi FVRS. Rangkaian pembelajaran yang mendalam, iaitu PCANet telah diperkenalkan. PCANet menpunyai tiga komponen pemprosesan asas data, iaitu penapis PCA, penyusunan binari bersepah dan histogram. PCA digunakan bagi pembelajaran bank penapis dari pelbagai lapisan. Penyusunan binari bersepah dan blok histogram merupakan langkah untuk pengindeksan dan penyatuan. Perbandingan antara PCANet dan PCA menunjukkan bahawa PCANet mendapat prestasi yang baik dalam contoh-contoh latihan yang minima, dengan peningkatan sebanyak 21.3% daripada PCA. Faktor-faktor yang mempunyai kesan terhadap prestasi PCANet telah dikaji untuk mengenal pasti batasan PCANet. Bagi klasifikasi, algoritma k- pendekatan jiran (kNN) dengan jarak Euclidean telah digunakan. Algoritma penambahbaikan kNN, iaitu k-pendekatan jiran umum (kGNN) pernah diperkenalkan pada permulaan. Akan tetapi, perbandingan prestasi antara kNN, kGNN dan SVM menunjukkan bahawa kNN lebih sesuai dalam FVRS. Peringkat terakhir dalam projek ini adalah mengabungkan kerja-kerja yang siap sebelum ini supaya dapat digunakan dalam keadaan sebenar. Program ini telah dimuatkan ke Raspberry Pi dengan menggunakan bahasa perisian C++ dan OpenCV. Penilaian prestasi menunjukkan bahawa ketepatan pengenalan FVRS mencapai 92.67%. PCANet telah menunjukkan potensi sebagai garis panduan yang mudah tetapi kompetitif dalam pengecaman urat jari. _______________________________________________________________________________________________________ Finger Vein Recognition System (FVRS) is a biometric technology that identifies or verifies an individual identity based on unique vein patterns. Compared with other biometrics, it is more secure, anti-forgery and hygiene. Thus, it successfully utilized in many authentications nowadays. The original FVRS developed only provides verification instead of identification. For identification, the image processing involves process of image pre-processing, feature extraction and classification. The project utilised pre-processing process such as edge detection, orientation correction and Region of Interest (ROI) extraction that have been developed previously. The main objective in this project is to implement a suitable feature extraction technique that can maximize the FVRS performance. A simple deep learning network, namely Principal Component Analysis Network (PCANet) is thus proposed. It composed of three basic data processing components, which are PCA filter, binary hashing and histograms. PCA is employed for learning multistage filter banks. Binary hashing and block histograms are the steps for indexing and pooling. A comparison between PCANet and PCA shows that PCANet is outperform under limited training samples, with an increase of 21.3% than that of PCA. Factors which impact PCANet are studied to identify the limitations of PCANet. For classification, k-Nearest Neighbours (kNN) with Euclidean distance algorithm is implemented. An enhancement version for kNN algorithm, k-General Nearest Neighbours (kGNN) have been proposed at initial stage. However, performance comparison between kNN, kGNN and SVM shows that kNN is more suitable for FVRS implementation. The last stage for this project is to combine previous work done into an embedded system which can be implemented in real finger vein authentication. The program is uploaded in the Raspberry Pi by using C++ language and OpenCV image processing library. The performance evaluation shows that the recognition rate of FVRS achieved 92.67% . Concluded that PCANet serve as a simple but highly competitive baseline in finger vein recognition.
Contributor(s):
Quek Ee Wen - Author
Primary Item Type:
Final Year Project
Identifiers:
Accession Number : 875007711
Language:
English
Subject Keywords:
Finger Vein Recognition System (FVRS); biometric technology; individual identity
First presented to the public:
6/1/2018
Original Publication Date:
8/10/2018
Previously Published By:
Universiti Sains Malaysia
Place Of Publication:
School of Electrical & Electronic Engineering
Citation:
Extents:
Number of Pages - 150
License Grantor / Date Granted:
  / ( View License )
Date Deposited
2018-08-14 12:40:11.396
Date Last Updated
2019-01-07 11:24:32.9118
Submitter:
Mohd Jasnizam Mohd Salleh

All Versions

Thumbnail Name Version Created Date
Raspberry pi-based finger vein recognition system using PCANet1 2018-08-14 12:40:11.396