Face recognition using neural network

مقدم أطروحة جامعية

al-Fahdawi, Khamis A. Zaydan

الجامعة

الجامعة التكنولوجية

الكلية

-

القسم الأكاديمي

قسم هندسة الحاسوب

دولة الجامعة

العراق

الدرجة العلمية

دكتوراه

تاريخ الدرجة العلمية

2004

الملخص الإنجليزي

Human faces are very similar in structure, with minor differences from person to person.

Furthermore, lighting condition changes, facial expressions, and pose variations further complicate the face recognition task, This thesis presents an efficient and low complexity hybrid approach to face recognition, which combines image preprocessing based on histogram equalization, wavelet transform and multi- neural networks. A face preprocessing approach is a histogram equalization to improve contrast and compensates for differences in camera input gains.

The preprocessed image is compressed to reduce the number of input pixels by using the wavelet transform to speed up the system and provide in variance to minor changes in the image samples. Multi-neural networks must be trained to deal with alt remaining variation (rotation, scale and deformation).

The outputs from multiple recognize must be combined into a single decision unit, that decide the classified face and associated information which is already stored in the database. The system recognize stimulus images correctly without being affected by shift in position, rotation, scaling, or by distortion in shape of these images because of using the arbitrate structure.

The system also recognizes images with changes in angle and express ion.

Small set of images per person in the training database is needed to produce acceptable classification accuracy.

The results obtained show that the proposed system gives a very encouraging performance. The proposed system structure was implemented as a software package "sing C++and visual Basic.

التخصصات الرئيسية

تكنولوجيا المعلومات وعلم الحاسوب

الموضوعات

• الشبكات العصبية(الحاسبات الإلكترونية)

• APA
• MLA
• AMA

لغة النص

الإنجليزية

نوع البيانات

رسائل جامعية

رقم السجل

BIM-306075