(For USM Staff/Student Only)

EngLib USM > Ω School of Chemical Engineering >

Pattern Recognition using clustering method

Pattern Recognition using clustering method / Dharishaan Vengadesan
Pengenalan muka telah menjadi satu isu penting dalam banyak aplikasi seperti sistem keselamatan, pengesahan kad kredit dan mengenal pasti penjenayah. Pengenalan muka adalah lebih selamat dalam sistem keselamatan kerana imej wajah telah digunakan sebagai ID. Ia juga membantu untuk mengelakkan sebarang peniruan pengenalan. Pengenalan muka membantu untuk mengenali imej muka terutama dalam mengenalpasti penjenayah tertentu. Mengenal pasti dan membandingkan wajah dalam imej adalah tugas yang sangat kompleks, ini telah melibatkan ramai penyelidik pada tahun-tahun terkini. Objektif projek ini adalah untuk merekabentuk dan membangunkan pengenalan muka menggunakan perisian MATLAB disamping memahami kaedah eigenfaces yang digunakan untuk mengiktiraf wajah imej. Ruang muka ditakrifkan oleh "eigenface", yang mana merupakan eigenvektor bagi sesuatu set muka, mereka tidak semestinya sesuai dengan ciri-ciri yang terpencil seperti mata, telinga dan hidung. Pendekatan eigenfaces seolah-olah menjadi satu kaedah yang mencukupi untuk digunakan dalam menghadapi pengiktirafan kepada kelajuan kesederhanaan, dan keupayaan pembelajaran. Keputusan kajian dilampirkan untuk menunjukkan daya maju cadangan kaedah pengenalan muka ini. _______________________________________________________________________________________________________ Face recognition has become an important issue in many applications such as security systems, credit card verification and criminal identification. Face recognition is more secure in security system because facial image had been used as the ID. It also helps to avoid any duplicated identification. Face recognition helps to recognize the facial image especially to indentifying certain criminals. Identifying and comparing faces in images is a very complex task, this is probably why it has attracted so many researchers in the latest years. Common method used in face recognition like eigenface method will be discussed. The objectives of this project are to design and develop a face recognition using MATLAB software beside to comprehend eigenfaces method of recognizing faces images. The face space is defined by the "eigenface", which are the eigenvectors of the set of faces, they do not necessarily correspond to isolated features such as eyes, ears and noses. Eigenfaces approach seems to be an adequate method to be used in face recognition due to its simplicity, speed and learning capability. Experimental results are given to demonstrate the viability of the proposed face recognition method. On the whole, when the system is modelled and tested, it was unreliable at times. The accuracy of the system was not high and has to be further improved.
Contributor(s):
Dharishaan Vengadesan - Author
Primary Item Type:
Final Year Project
Identifiers:
Accession Number : 875007515
Language:
English
Subject Keywords:
Face recognition; important; security system
First presented to the public:
5/1/2018
Original Publication Date:
7/18/2018
Previously Published By:
Universiti Sains Malaysia
Place Of Publication:
School of Chemical Engineering
Citation:
Extents:
Number of Pages - 49
License Grantor / Date Granted:
  / ( View License )
Date Deposited
2018-07-31 11:32:13.868
Date Last Updated
2019-01-07 11:24:32.9118
Submitter:
Mohd Jasnizam Mohd Salleh

All Versions

Thumbnail Name Version Created Date
Pattern Recognition using clustering method1 2018-07-31 11:32:13.868