(For USM Staff/Student Only)

EngLib USM > Ω School of Electrical & Electronic Engineering >

Ensemble of multiple matchers for finger vein recognition

Ensemble of multiple matchers for finger vein recognition / Soh Siang Loong
Sistem pengiktirafan biometrik merupakan sistem yang amat penting dalam pengenalan dan pengesahan individu. Penyelidikan bagi pengesahan saluran darah jari semakin popular disebabkan manfaat-manfaat yang diperoleh seperti kebersihan dan tidak boleh ditiru. Selain itu, pengesahan saluran darah jari juga dapat mengatasi keperluan masyarakat dan masalah kesihatan. Pelbagai kaedah pengekstrakan ciri telah dicadangkan oleh penyelidik, seperti pengesanan garis berulang kali, “Principal Component Analysis” (PCA), “Linear Discriminant Analysis” (LDA) dan Saluran Terhad Fasa Sahaja Korelasi (BLPOC). Kaedah-kaedah tersebut dikategorikan sebagai pengekstrakan ciri secara buatan tangan. Pengekstrakan ciri secara belajar masih tidak pernah digunakan dalam saluran darah jari. Jadi, pengumpulan data secara piramid digunakan dalam pengekstrakan ciri saluran darah jari. BLPOC digunakan sebagai pengekstrakan ciri secara buatan tangan. Skor-skor yang diperoleh akan digabungkan dengan skor-skor yang diperoleh dari pengumpulan data secara piramid dengan menggunakan Mesin Vektor Sokongan (SVM). Pangkalan data FV-USM yang diguna terdiri daripada 123 individu, imej saluran darah 4 jari bagi setiap individu ditangkap. Kadar Kesilapan Sama (EER) bagi pengumpulan data secara piramid adalah paling tinggi, sebanyak 4.368%, diikuti dengan BLPOC, 2.36% dan SVM mempunyai EER yang paling rendah 0.1348%. Konklusinya, gabungan antara pengekstrakan ciri secara belajar dan secara buatan tangan menunjukkan keputusan yang lebih baik dibandingkan dengan pemadanan ciri secara tunggal. _______________________________________________________________________________________________________ Biometrics recognition system is important in identification and verification of an individual. Recently, the research on finger vein verification becomes popular due to the benefits such as hygiene and cannot be duplicated. Finger vein verification is also able to overcome community needs and health problems. Various feature extraction methods were proposed by researchers, such as repeated line tracking, Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA), and Band-Limited Phase-Only Correlation (BLPOC. These methods are considered as hand-crafted feature extraction method. Learned feature extraction has not been used in finger vein verification yet. Hence, spatial pyramid pooling method is developed as learned feature extraction for finger vein verification. BLPOC is used as hand-crafted feature extraction which the scores obtained will be then fused together with the scores obtained from spatial pyramid pooling by using Support Vector Machine (SVM). The database used is FV-USM based on 123 individuals with 4 fingers each. In the result obtained, spatial pyramid pooling shows the highest EER, 4.368%, followed by BLPOC, 2.36% and the lowest is SVM, 0.1348%. As conclusion, fusion of learned feature and hand-crafted feature shows the best performance as compared to single feature matching.
Contributor(s):
Soh Siang Loong - Author
Primary Item Type:
Final Year Project
Identifiers:
Accession Number : 875007126
Barcode : 00003107004
Language:
English
Subject Keywords:
Biometrics recognition system; finger vein verification; hand-crafted feature extraction method
First presented to the public:
6/1/2017
Original Publication Date:
4/20/2018
Previously Published By:
Universiti Sains Malaysia
Place Of Publication:
School of Electrical & Electronic Engineering
Citation:
Extents:
Number of Pages - 70
License Grantor / Date Granted:
  / ( View License )
Date Deposited
2018-04-20 15:37:13.834
Date Last Updated
2019-01-07 11:24:32.9118
Submitter:
Mohd Jasnizam Mohd Salleh

All Versions

Thumbnail Name Version Created Date
Ensemble of multiple matchers for finger vein recognition1 2018-04-20 15:37:13.834