(For USM Staff/Student Only)

EngLib USM > Ω School of Electrical & Electronic Engineering >

Iris recognition system (irs) using deep learning technique

Iris recognition system (irs) using deep learning technique / Yow Sue Chin
Pengesahan biometrik semakin canggih dengan kemajuan teknologi, terutamanya pemprosesan imej progresif dan keupayaan pengkomputeran. Pengiktirafan melalui organ iris manusia adalah salah satu biometrik yang popular kerana ia menjanjikan pulangan yang lebih janji dalam penglihatan mesin, kebolehpercayaan dan mudah berbanding dengan ciri-ciri lain. Pembelajaran mesin bergantung kepada input sample data yang masuk, dan lakukan klasifikasi pada sampel data. Akhirnya, ramalkan output berdasarkan kebarangkalian. Untuk teknik sistem pengenalan klasik yang sebelumnya, segmentasi iris dengan tepat adalah peringkat penting dalam menjamin ketepatan yang tinggi untuk Sistem Pengiktirafan Iris (IRS). Oleh itu, keperluan dataset imej mesti diperolehi dalam keadaan khusus, jika tidak, ia mengakibatkan kegagalan dalam segmen iris kerana set hyperparameters atau algoritma tidak sesuai untuknya. Penalaan hyperparameter manual pada model Pembelajaran Mesin mungkin mengambil masa dan kegagalan jika tidak memahami sepenuhnya pada algoritma dan ciri-ciri dataset berfungsi. Dalam tesis ini, pembelajaran pemindahan dicadangkan untuk memanfaatkan model ConvNet yang terlatih dalam Pertandingan Pengiktirafan Visual Skala Besar ImageNet (ILSVRC) ke atas IRS. Analisis sistematik telah dilakukan untuk merekabentuk rangkaian yang mendalam untuk mencapai kecekapan tinggi dalam pengekstrakan ciri. Model AlexNet dan DenseNet201 yang memiliki pelbagai seni bina Rangkaian Neural Convolution (ConvNet) dan kedalaman lapisan dipilih dan diubah menjadi algoritma untuk pengiktirafan iris. Pertama, dataset CASIA-Iris-Interval V1 dipilih sebagai sasaran iris dataset untuk dilatih. Kemudian, penilaian ke atas prestasi IRS selepas menggunakan teknik perkembangan data dan pengoptimuman hyperparameter. Semua hasil yang direkodkan sepanjang proses pembangunan algoritma menunjukkan kejayaan metodologi yang dicadangkan dalam memperolehi algoritma prestasi yang lebih tinggi. Mengikut aliran metodologi yang dicadangkan, AlexNet mencapai ketepatan keseluruhan 97,22% sementara DenseNet201 mencapai ketepatan keseluruhan 98,81%. Pemindahan model pra terlatih pada tugas sasaran baru ditingkatkan dan sementara itu, kadar pengiktirafan yang tinggi pada dataset imej iris CASIA-Iris-Interval V1 bersaiz kecil dapat dicapai. _______________________________________________________________________________________________________ Biometric authentication becomes sophisticated with the advance of technology, especially progressive image processing, and computational capabilities. Iris recognition through human iris organ is one of the popular biometrics as it is promising higher accurate return in machine vision, reliability and simpler as compared to other traits. Machine Learning depends on the input fit in, do classification on the sample data. Finally, predict the output based on the probability. For the previous classical recognition system technique, accurate iris segmentation is the crucial part to guarantee high accuracy for Iris Recognition System (IRS). Hence, the requirement of the image dataset has to acquire under specific conditions, else it might be failed in iris segmentation as well as the hyperparameters set or algorithms applied unsuitable for it. Manual hyperparameter tuning on Machine Learning model may take time and failure if not fully understand the algorithms and feature of datasets work with. In this thesis, the Transfer Learning method is proposed to capitalize pre-trained Convolutional Neural Network (ConvNet) model introduced in the ImageNet Large Scale Visual Recognition Competition (ILSVRC) on the IRS. Systematic analysis has been conducted to design an optimal deep network architecture to achieve high efficiency in feature extraction. AlexNet and DenseNet201 pre-trained model that poses different ConvNet architecture and layer depth were chosen and trained Support Vector Machine (SVM) for testing model transferability. CASIA-Iris-Interval V1 dataset is then re-trained on AlexNet and DenseNet201 model one by one. Finally, evaluation of the IRS performances after applying Data Augmentation and Bayesian Optimization. All the results recorded along the algorithm development process showed the success of proposed methodologies in gaining a higher performance algorithm. Undergo proposed methodology flow, AlexNet achieved an overall accuracy of 97.22% meanwhile DenseNet201 achieved an overall accuracy of 98.81%. Transferability of a pre-trained model on new target task is improved and meanwhile, the high recognition rate of the algorithm on small-size CASIA-Iris-Interval V1 iris image dataset is achieved.
Contributor(s):
Yow Sue Chin - Author
Primary Item Type:
Final Year Project
Identifiers:
Accession Number : 875008599
Language:
English
Subject Keywords:
Biometric; advance; Iris
First presented to the public:
6/1/2019
Original Publication Date:
2/26/2020
Previously Published By:
Universiti Sains Malaysia
Place Of Publication:
School of Electrical & Electronic Engineering
Citation:
Extents:
Number of Pages - 86
License Grantor / Date Granted:
  / ( View License )
Date Deposited
2020-02-26 18:06:09.135
Date Last Updated
2020-12-10 16:26:41.513
Submitter:
Mohd Jasnizam Mohd Salleh

All Versions

Thumbnail Name Version Created Date
Iris recognition system (irs) using deep learning technique1 2020-02-26 18:06:09.135