(For USM Staff/Student Only)

EngLib USM > Ω School of Electrical & Electronic Engineering >

Real-time face detection and tracking using software and hardware design

Real-time face detection and tracking using software and hardware design / Chen Kok Keat
Projek ini menyampaikan reka bentuk dan pelaksanaan sistem pemprosesan video iaitu algoritma pengesanan muka manusia dalam FPGA. Pengesanan dan penjejakan muka telah menjadi bidang penyelidikan yang aktif disebabkan terdapat banyak aplikasi yang penting, contohnya, pengawasan video, biometrik, pengekodan video dan lain-lain lagi. Matlamat projek ini adalah untuk melaksanakan satu sistem video dengan masa sebenar dalam FPGA bagi pengesanan muka manusia. Projek algoritma pengesanan muka ini adalah berdasarkan segmentasi warna kulit manusia dan penapisan imej/video. Lokasi muka adalah ditentukan dengan kiraan centroid kawasan muka yang dikesan. Satu algoritma berversi perisian telah dilaksanakan secara bebas dan diuji dalam MATLAB/Simulink. Walaupun peralihan daripada pengekodan berversi perisian kepada kod berbahasa Verilog HDL adalah tidak betul-betul sama, keputusan daripada eksperimen membuktikan fungsi, ketepatan, dan keberkesanan sistem video masa sebenar ini. Bagi pelaksanaan FPGA, keseluruhan algoritma pengesanan muka boleh dilaksanakan pada peranti Cyclone IV FPGA dengan menggunakan Altera DE2-115. Video atau imej input daripada satu kamera iaitu Terasic Capacitive Multi-Touch LCD with Camera Module (MTLC) manakala sistem output dipaparkan pada satu monitor VGA. Kesemua pengiraan dalan pelaksanaan perkakasan FPGA adalah dilakukan dalam masa sebenar dengan usaha pengkomputeran minimum, maka sesuai untuk penggunaan kuasa terhad. _______________________________________________________________________________________________________ This project presents the design and the implementation of face detection algorithm for video processing applications on FPGAs. Face detection and tracking has been an active research topic because it offers many important applications, especially in video surveillance, biometrics, video coding and so on. The goal of this project was to implement a real-time system on an FPGA to detect and track human faces. The face detection algorithm involved colour-based skin segmentation and image filtering. The face location was determined by calculating the centroid of the detected region. A software version of the algorithm was independently implemented and tested in MATLAB Simulink. Although the transition from software version to HDL (Verilog) was not exactly the same between both approaches, experimental results proved the functionality, accuracy and effectiveness of the real-time system, even under varying conditions of lights, facial poses and skin colours. For FPGA implementation the entire face detection algorithm was implemented on Cyclone IV FPGA device using Altera DE2-115. The input video or image came from a Terasic Capacitive Multi-Touch LCD with Camera Module (MTLC) and the outputs were displayed on a VGA monitor. All calculations of the hardware implementation were done in real time with minimal computational effort, thus suitable for power-limited applications.
Contributor(s):
Chen Kok Keat - Author
Primary Item Type:
Final Year Project
Identifiers:
Accession Number : 875007719
Language:
English
Subject Keywords:
face detection; video processing; human faces
First presented to the public:
6/1/2018
Original Publication Date:
8/16/2018
Previously Published By:
Universiti Sains Malaysia
Place Of Publication:
School of Electrical & Electronic Engineering
Citation:
Extents:
Number of Pages - 93
License Grantor / Date Granted:
  / ( View License )
Date Deposited
2018-09-05 10:31:41.095
Date Last Updated
2019-01-07 11:24:32.9118
Submitter:
Mohd Jasnizam Mohd Salleh

All Versions

Thumbnail Name Version Created Date
Real-time face detection and tracking using software and hardware design1 2018-09-05 10:31:41.095