(For USM Staff/Student Only)

EngLib USM > Ω School of Electrical & Electronic Engineering >

Developement of audio-visual biometric verification system with the integration of fuzzy inference system (fis)

Developement of audio-visual biometric verification system with the integration of fuzzy inference system (fis) / Tay Chui Hui
Sistem pengesahan biometrik adalah sistem yang menggunakan maklumat fisiologi dan tingkah laku untuk mengesahkan seseorang individu. Sistem pengesahan biometrik tunggal menunjukkan kebolehpercayaan yang tinggi dalam keadaan persekitaran yang bersih dari hingar. Walau bagaimanapun, dalam persekitaran hingar, kebolehpercayaan pengesahan biometrik tunggal jatuh secara mendadak. Sistem pengesahan berbilang biometrik dibangunkan untuk menangani masalah yang dihadapi oleh sistem pengesahan biometrik tunggal. Dalam projek ini, sistem pengesahan biometrik suara, visual dan suara-visual telah dibangunkan. Kesemua system ini telah diuji prestasinya pada tahap hingar yang berbeza bagi mengetahui tahap ketegaran sistem. Dalam kajian ini, analisa Pengekodan Peramalan Linear (LPC) telah digunakan untuk mengektrak ciri suara manakala Kawasan Dikehendaki (ROI) bagi imej bibir digunakan sebagai ciri visual.. Mesin Penyokong Vektor (SVM) pula digunakan sebagai pengelas. Sistem pengesahan biometrik suara-visual yang dibangunkan dalam projek ini disepadukan dengan sistem inferens logik kabur (FIS). FIS memberikan nilai pemberat yang optimum untuk digunakan dalam sistem pengesahan biometrik suara visual. Prestasi sistem pengesahan biometrik suara, visual dan suara-visual yang diuji di bawah pelbagai tahap hingar disahkan dengan menggunakan graf Kadar Penerimaan Tulen (GAR) melawan kadar penerimaan palsu (FAR). Hasil keputusan ekperimen menunjukkan system biometrik suara-visual sentiasa lebih baik berbanding sistem biometrik tunggal. Sebagai contohnya, pada FAR bersamaan 0.2%, 66%, 69% and 90% GAR diperhatikan untuk sistem pengesahan biometrik suara, visual dan suara-visual masing-masing (isyarat suara pada 10dB dan isyarat visual pada 0.05 sigma) _______________________________________________________________________________________________________ Biometric verification system is the system that uses physiological and behavioral information to verify an individual. Single biometric verification system shows high reliability in clean noise free condition. However, in the noisy environment, the reliability of the single biometric verification drops drastically. Multi-biometric verification system is developed to deal with the problem faced by single biometric verification system. In this project, voice, visual and audio-visual biometric verification systems are developed. These systems have been evaluated at different noise levels in order to investigate their robustness. In this study, Linear Predictive Coding (LPC) analysis has been used to extract the audio features while Region of Interest (ROI) of lip image has been used as visual features. Support Vector Machine (SVM) is then employed as classifier. The audio-visual biometric verification developed in this project is integrated with the Fuzzy Inference System (FIS). FIS infers the optimum weight to be used as fusion weight in audio-visual biometric verification system. The performances of the audio, visual and audio-visual verification systems are evaluated under various noise levels are verified using the Genuine Acceptance Rate (GAR) versus False Acceptance Rate (FAR) curves. From the experimental results, audio-visual biometric system always outperforms the performances of the single systems. For example at 0.2% FAR, 66%, 69% and 90% of GAR are observed for audio, visual and audio-visual biometric systems, respectively (audio signal at 10dB and visual signal at 0.05 sigma) .
Contributor(s):
Tay Chui Hui - Author
Primary Item Type:
Final Year Project
Identifiers:
Barcode : 00003096351
Accession Number : 875004730
Language:
English
Subject Keywords:
Biometric; Linear Predictive Coding; Support Vector Machine
First presented to the public:
6/1/2012
Original Publication Date:
3/9/2018
Previously Published By:
Universiti Sains Malaysia
Place Of Publication:
School of Electrical & Electronic Engineering
Citation:
Extents:
Number of Pages - 107
License Grantor / Date Granted:
  / ( View License )
Date Deposited
2018-03-09 11:25:01.123
Date Last Updated
2019-01-07 11:24:32.9118
Submitter:
Mohd Jasnizam Mohd Salleh

All Versions

Thumbnail Name Version Created Date
Developement of audio-visual biometric verification system with the integration of fuzzy inference system (fis)1 2018-03-09 11:25:01.123