2016_Feature Reduction Techniques To Enhance Face Recognition

Bibliographic Details
Format: General Document
_version_ 1860798151074512896
building INTELEK Repository
collection Online Access
collectionurl https://intelek.unisza.edu.my/intelek/pages/search.php?search=!collection3
copyright Copyright©PWB2025
country Malaysia
date 2016-08-07
format General Document
id 16193
institution UniSZA
originalfilename FEATURE REDUCTION TECHNIQUES TO ENHANCE FACE RECOGNITION.pdf
person Zahradden Sufyanu
recordtype oai_dc
resourceurl https://intelek.unisza.edu.my/intelek/pages/view.php?ref=16193
sourcemedia Server storage
Scanned document
spelling 16193 https://intelek.unisza.edu.my/intelek/pages/view.php?ref=16193 https://intelek.unisza.edu.my/intelek/pages/search.php?search=!collection3 General Document Malaysia Library Staff (Top Management) Library Staff (Management) Library Staff (Support) Terengganu Faculty of Informatics & Computing English application/pdf 1.5 Server storage Scanned document Universiti Sultan Zainal Abidin UniSZA Private Access UNIVERSITI SULTAN ZAINAL ABIDIN SAMBox 2.4.24; modified using iTextSharp™ 5.5.10 ©2000-2016 iText Group NV (AGPL-version) Copyright©PWB2025 287 Face—Recognition 2016-08-07 FEATURE REDUCTION TECHNIQUES TO ENHANCE FACE RECOGNITION.pdf Face—Recognition Zahradden Sufyanu 2016_Feature Reduction Techniques To Enhance Face Recognition Face processing provides a user-friendly and nonintrusive means of human identificafion. The fundamental problems in face identification are uncontrolled illumination conditions and high degree of features complexity. Many studies focus on illumination normalization and dimensionality reduction. Yet, simplistic and realistic criteria are demanded. ln this thesis, a fiamework that enhances feature selection for simultaneous detection and recognition of face using Hough Transform (HT) is introduced. Subsequently, Anisotropic Diffusion Illumination Normalization technique based DCT (ASDCT) is proposed to compensate illumination and improve the decorrelation of features. Meanwhile, an algorithm named 'lntegrated Histograms based on Discrete Cosine Transform' (HIDCT) is developed to increase data compaction and reduce redundancy. Reduced number of features is obtained through rotating histogram plots by 30 degrees. Then HT maffices are extracted for face recognition. The best illumination normalization technique is known by comparing 22 illumination normalization techniques in the literature. Then 19 coefficients with largest magnitude are selected. Discrete Cosine Transform (DCT) is exploited on the reduced features to form new coefficients that optimize lossy compression techniques. The performance of the system is tested using standard research databases. Template matching and nearest neighbor classifiers are used for similarity measuements. Experimental results indicated that, the enhanced framework is very effective and accomplished an average detection time of 1.199 seconds, and minimum recognition accuracy of 95.6250/o. ASDCT technique showed up to 97.700o/o veification rate at I .0% of False Acceptance Rate (FAR). This supersedes Appearance based techniques such as Linear Discriminant Analysis (LDA), and Kemel Principal Component Analysis (KPCA). The level of compression of HIDCT algorithm is at least three times the conventional DCT. The proposed HIDCT is simple to implement and can accommodate large users within a small memory space. Furthermore, the tkee fiameworks encourage real world applications for efficient identifications. Dissertations, Academic Facial Recognition Systems Feature Reduction Thesis
spellingShingle 2016_Feature Reduction Techniques To Enhance Face Recognition
state Terengganu
subject Face—Recognition
Dissertations, Academic
summary Face processing provides a user-friendly and nonintrusive means of human identificafion. The fundamental problems in face identification are uncontrolled illumination conditions and high degree of features complexity. Many studies focus on illumination normalization and dimensionality reduction. Yet, simplistic and realistic criteria are demanded. ln this thesis, a fiamework that enhances feature selection for simultaneous detection and recognition of face using Hough Transform (HT) is introduced. Subsequently, Anisotropic Diffusion Illumination Normalization technique based DCT (ASDCT) is proposed to compensate illumination and improve the decorrelation of features. Meanwhile, an algorithm named 'lntegrated Histograms based on Discrete Cosine Transform' (HIDCT) is developed to increase data compaction and reduce redundancy. Reduced number of features is obtained through rotating histogram plots by 30 degrees. Then HT maffices are extracted for face recognition. The best illumination normalization technique is known by comparing 22 illumination normalization techniques in the literature. Then 19 coefficients with largest magnitude are selected. Discrete Cosine Transform (DCT) is exploited on the reduced features to form new coefficients that optimize lossy compression techniques. The performance of the system is tested using standard research databases. Template matching and nearest neighbor classifiers are used for similarity measuements. Experimental results indicated that, the enhanced framework is very effective and accomplished an average detection time of 1.199 seconds, and minimum recognition accuracy of 95.6250/o. ASDCT technique showed up to 97.700o/o veification rate at I .0% of False Acceptance Rate (FAR). This supersedes Appearance based techniques such as Linear Discriminant Analysis (LDA), and Kemel Principal Component Analysis (KPCA). The level of compression of HIDCT algorithm is at least three times the conventional DCT. The proposed HIDCT is simple to implement and can accommodate large users within a small memory space. Furthermore, the tkee fiameworks encourage real world applications for efficient identifications.
title 2016_Feature Reduction Techniques To Enhance Face Recognition
title_full 2016_Feature Reduction Techniques To Enhance Face Recognition
title_fullStr 2016_Feature Reduction Techniques To Enhance Face Recognition
title_full_unstemmed 2016_Feature Reduction Techniques To Enhance Face Recognition
title_short 2016_Feature Reduction Techniques To Enhance Face Recognition
title_sort 2016_feature reduction techniques to enhance face recognition