عنوان المقالة:ENHANCEMENT OF LBP-BASED FACE IDENTIFICATION SYSTEM BY ADOPTING PREPROCESSING TECHNIQUES ENHANCEMENT OF LBP-BASED FACE IDENTIFICATION SYSTEM BY ADOPTING PREPROCESSING TECHNIQUES
ا.د. محمد عصام يونس | Mohammed I. Younis | 14092
نوع النشر
مجلة علمية
المؤلفون بالعربي
محمد عصام يونس , رأفت صالح محمد
المؤلفون بالإنجليزي
Mohammed Issam Younis, Raafat Salih Muhammad
الملخص العربي
. Face identification system is an active research area in these years. However, the accuracy and its dependency in real life systems are still questionable. Earlier research in face identification systems demonstrated that LBP based face recognition systems are preferred than others and give adequate accuracy. It is robust against illumination changes and considered as a high-speed algorithm. Performance metrics for such systems are calculated from time delay and accuracy. This paper introduces an improved face recognition system that is build using C++ programming language with the help of OpenCV library. Accuracy can be increased if a filter or combinations of filters are applied to the images. The accuracy increases from 95.5% (without applying any filter) to 98.5% when applying a combination of Bilateral filter, Histogram Equalization and Tan and Triggs Algorithm. Finally, the results show degradation in accuracy and increasing in recognition time if images database get bigger.
الملخص الانجليزي
Face identification system is an active research area in these years. However, the accuracy and its dependency in real life systems are still questionable. Earlier research in face identification systems demonstrated that LBP based face recognition systems are preferred than others and give adequate accuracy. It is robust against illumination changes and considered as a high-speed algorithm. Performance metrics for such systems are calculated from time delay and accuracy. This paper introduces an improved face recognition system that is build using C++ programming language with the help of OpenCV library. Accuracy can be increased if a filter or combinations of filters are applied to the images. The accuracy increases from 95.5% (without applying any filter) to 98.5% when applying a combination of Bilateral filter, Histogram Equalization and Tan and Triggs Algorithm. Finally, the results show degradation in accuracy and increasing in recognition time if images database get bigger.
تاريخ النشر
01/06/2017
الناشر
Inventi Impact - Image & Video Processing
رقم المجلد
2017
رقم العدد
2
ISSN/ISBN
2277-2332
الصفحات
68-74
رابط الملف
تحميل (491 مرات التحميل)
رابط خارجي
http://inventi.in/journal/article/impact/91/21844/image-video-processing/h#
الكلمات المفتاحية
Face Recognition; LBP; Recognition accuracy; Recognition time
رجوع