Hand recognition method based on Eigen-hand (principal component analysis)‎ technique

العناوين الأخرى

طريقة اليد المستندة على تقنية تحليل المركبات الأساسية للأيدي الذاتية

مقدم أطروحة جامعية

Hamid, Husayn Abd Allah

مشرف أطروحة جامعية

Ali, Salih Mahdi

أعضاء اللجنة

al-Zuki, Ali Abd D.
Dakhil, Zahidah Ahmad
Ghazal, Nawal Khalaf

الجامعة

جامعة بغداد

الكلية

كلية العلوم

القسم الأكاديمي

قسم الفيزياء

دولة الجامعة

العراق

الدرجة العلمية

ماجستير

تاريخ الدرجة العلمية

2011

الملخص الإنجليزي

In this thesis, the Principal Component Analysis (PCA) based method (namely Eigenhand), is used to verify persons from their hand’s image.

Our approach treats the hand recognition and verification problems as an essentially 2D-problem rather than requiring recovery of 3D geometry, taking advantage of the fact that hand’s images can be described by a small set of 2D characteristics features.

The extracted features for the recognition process have been referred to as “Eigen hands” because they represent the eigenvectors of the set of the trained and tested hands.

The verification operation between the trained hand’s images (i.e.

preserved in the Database) and the input “unknown” hand image is performed by utilizing the Minimum-Mean- Distance “MMD” criterion.

The designed system output is either "Verified" or "Unverified".

Several amounts of different noises (e.g.

Gaussian, Salt-and-pepper, Uniform) have been added to the tested hand to measure the reliability of our presented verification system.

Additionally, the effects of image rotation have, also, been studied by rotating the test image few degrees (in clock and anti-clock directions).

Moreover, the scaling effects have also be checked by enlarging the test image several percentage amount, and shifting (directionality left and right) have also been carried out

التخصصات الرئيسية

الفيزياء

عدد الصفحات

90

قائمة المحتويات

• APA
• MLA
• AMA

لغة النص

الإنجليزية

نوع البيانات

رسائل جامعية

رقم السجل

BIM-606337