In this paper an evaluation of image keypoints detectors and descriptors is presented
when used for building panoramic image. The descriptors: (SIFT, SURF, BRIEF, ORB,
BRISK, and FREAK) were discussed, when used with the appropriate keypoints detec
tors
on database taken indoors by RGB-D camera. Crosscheck and RANSAC (RANdom
Sample Consensus) algorithms were used to find transform matrix between images. The
speed of keypoints detectors and descriptors, the matching speed, the average of extracted
keypoints, recall and precision were investigated. Oxford dataset was used to find the best
descriptor for dealing with rotation and illumination changes that might occur due to
changes in illumination angle.
The obtained results showed that SIFT was the keypoint descriptor with the highest
performance in non-real time applications. The SURF/BRISK was the best
detector/descriptor which can be used in real time applications with comparable SIFT's
results.
The aim of the work is to improve the performance of the WLD
descriptor using Gabor filters in a preprocessing stage. The
performance of the improved descriptor will be compared with the
performance of the LBP descriptor(a widely used descriptor i
n FER
researches). This performance will be achieved using the extremely
used expert system SVM besides the expert systems CSD and MLP.
التعرف على تعابير الوجه
النماذج الثنائية المحلية
واصف ويبر المحلي
نماذج غير المحلية الثنائية
واصف ويبر-غيبر المحلي
مرشح غيبر
الشبكة العصبونية متعددة الطبقات
أداة الأشعة الداعمة
مسافة تشي التربيعية
FER-Facial Expression Recognition
LBP-Local Binary Pattern
WLD-Weber Local Descriptor
LGBP-Local Gabor Binary Pattern
WGLD-Weber Gabor Local Descriptor. Gabor filter
MLP-Multi Layer Perceptron
SVM- Support Vector Machine
CSD- Chi squared distance
المزيد..