- 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
Face Recognition and Retrieval based on Wavelet Transform Using Association Rules in Android Operating System | ||
| Iraqi Journal of Information Technology | ||
| Article 1, Volume 7, Issue 2, 2017, Pages 98-117 | ||
| Authors | ||
| Abdul-Wahab Sami Ibrahim; Raniah Ali Mustafa | ||
| Abstract | ||
| In this paper, we propose face detection approach was successfully implemented on Android Operating System version (4.3) which involved programming in Java language version 6 and face recognition system successfully implemented in programming language visual basic 6.0. The main idea of the proposed system depends on the fact that any face image person has multi unique features. These features are different from one face image to another. Our proposed algorithm depends on wavelet transform to extract features from the face image person to extract association rules between these features to recognition face images person and retrieval. And then each face image is stored with its association rules in the association rules database to be used in face image recognition and retrieval systems. From experiments and test results it is noted that behavior of proposed face detection approach leads to higher detection performance results, face recognition and retrieval approach leads to higher performance results for most classes. The system was tested over a database collected from 30 volunteers, where 15 images for each person were collected under different lighting conditions, varied in expression, orientations, illumination, skin color, background, ages, and faces shapes (the mouth and eyes are open or closed, with or without glasses, male and female... etc.). The achieved training rate was 100% and recognition rate (72%) and the average of precision (70.5%) were achieved. | ||
| Keywords | ||
| Face Recognition; RGB color space; discrete wavelet transform; Data Mining; Association Rules; CONTENT; based Image Retrieval; Android Operating System | ||
|
Statistics Article View: 181 PDF Download: 3 |
||