- All Journals
- Al-Qadisiyah University
- Basrah University
- Kirkuk University
- Mosul University
- The Iraqi Borad for Medical Specialization
- University of Anbar
- University of Technology
- Al Mustafa University
- Al-Zahraa University for Women
- Alnoor University
- Kunooz University
- Misan University
- Ninevah University
- Tikrit University
- University of Al-Hamdaniya
- University of Kerbala
Implemented a Facial Recognition Based on Fractal Coding and Quadtree Techniques | ||
| Diyala Journal For Pure Science | ||
| Article 1, Volume 13, Issue 4, 2017, Pages 160-182 | ||
| Authors | ||
| Raheem Abdul-Al Sahib Ogla; Yasser Dhiaa Jawad | ||
| Abstract | ||
| The research aims to design and implement a hybrid algorithm through a combination of fractal coding and quad tree algorithms to build revealed the identity of persons through the recognition of the human characteristics for the destination system. The work is implemented through two phases the first phase is detection phase (Training Phase), to discover information of skin complexion and stored them in the database, some critical coefficient parameters are extracted and stored in coding file like Peak Signal-to-Noise Ratio (PSNR), offset bits, Scale bits, mean absolute error (MAE), width and height of the cutting face these coefficient parameters are computed based on coding fractal scheme algorithm.The second phase is the stage of recognition of persons. It is carried out through matching extracted information in the discrimination phase with the information stored in the database in the detection phase. At the stage of discrimination, quad tree algorithm is used as an algorithm searching and matching at the same time in order to accelerate the matching process in both phases as a solution to the problem (wasted time) faced by the fractal algorithm. The work is implemented on color images, with various directions images (forward, 10o, 15o, 20o, 25o, 30o, 35o) the database has been trained on a standard database (MIT) as well as through the images in real time. Experimental results proved that the speedup matching between image faces stored and their information in the database and the image faces want to distinguish them was very high (0.0 1sec), and the accuracy ranged matching between (89% -92%) . | ||
| Keywords | ||
| Facial detection; Facial recognition; Image Processing; Quadtree | ||
|
Statistics Article View: 69 PDF Download: 18 |
||