Efficient Techniques For Human Face Occlusions Detection and Extraction

Nowadays, Facial occlusion is an interesting problem. It strongly affects the efficiency of the face recognition systems. This work is based on human face analysis to extract three types of occlusions using artificial intelligence techniques. Indeed, we are interested in beard and mustache, also eye...

Full description

Saved in:
Bibliographic Details
Published in2021 International Conference of Women in Data Science at Taif University (WiDSTaif ) pp. 1 - 5
Main Authors Sghaier, Souhir Moncef, Elfaki, Abir Othman
Format Conference Proceeding
LanguageEnglish
Published IEEE 30.03.2021
Subjects
Artificial intelligence
beard
biometric
Data mining
Data science
Detectors
eyeglasses
Face recognition
Filtering algorithms
human face
Morphological operations
mustache
Online AccessGet full text

Cover

More Information
Summary:Nowadays, Facial occlusion is an interesting problem. It strongly affects the efficiency of the face recognition systems. This work is based on human face analysis to extract three types of occlusions using artificial intelligence techniques. Indeed, we are interested in beard and mustache, also eyeglasses detection, and extraction. We begin with the extraction of the face of the person. Using Viola-Jones algorithm based on Vision Cascade Detector. Then, the extraction of the beard and the mustache are used using two performance methods; the first using the Fuzzy C-means method, the second is using filters and morphological operations. After that, we detect the presence of the eyeglasses. The methods applied to show honorable results.
DOI:10.1109/WiDSTaif52235.2021.9430214