A multi-layer perceptron neural network based-model for face detection

مقدم أطروحة جامعية

al-Qudah, Ghayth Ahmad

مشرف أطروحة جامعية

Shilbayah, Nidal F.

أعضاء اللجنة

al-Mamluk, Rustum
al-Shammari, Husayn Hadi Uwayyid
Salamah, Walid

الجامعة

جامعة الشرق الأوسط

الكلية

كلية تكنولوجيا المعلومات

القسم الأكاديمي

قسم علم الحاسوب

دولة الجامعة

الأردن

الدرجة العلمية

ماجستير

تاريخ الدرجة العلمية

2009

الملخص الإنجليزي

We propose a face detector using an efficient architecture based on a multi layerperceptron neural network (MLPNN) with maximal rejection classifier (MRC) which we achieve enhanced detection accuracy and efficiency using matlab.

First, experimental results show that the proposed neural-network significantly improves the detection accuracy as compared to traditional neural-network-based techniques.

Second, in order to reduce the total computation cost for the face detection, we organize the neural network in this way, simply used at earlier stages are able to reject a majority of non-face patterns in the image backgrounds, thereby significantly improving the overall detection efficiency while maintaining the detection accuracy.

An important advantage of the new architecture is that it has a homogeneous structure so that it is suitable for very efficient implementation using programmable devices.

Our proposed approach achieves one of the best detection accuracies with significantly reduced training and detection cost.

The goal of this project is to detect and locate human faces in a color image.

A set of training images were provided for this purpose.

The objective was to design and implement a face detector in MATLAB and Visual Studio .NET that will detect human faces in an image similar to the training images.

التخصصات الرئيسية

تكنولوجيا المعلومات وعلم الحاسوب

عدد الصفحات

49

قائمة المحتويات

• APA
• MLA
• AMA

لغة النص

الإنجليزية

نوع البيانات

رسائل جامعية

رقم السجل

BIM-693922