Title :
Detecting face-looking images
Author :
Abaci, Bahri ; Akgul, Tayfun
Author_Institution :
Elektron. ve Haberlesme Muhendisligi Bolumu, Istanbul Tek. Univ., Istanbul, Turkey
Abstract :
Human beings tends to see face-like images as faces. In this study, a new face-looking database is created and an automatic method which recognizes such face-looking images as faces, has been developed. The average success rate of the algorithm is 57%.
Keywords :
face recognition; visual databases; automatic face-looking image recognition; average success rate; face-looking database; face-looking image detection; Computer vision; Conferences; Databases; Face recognition; Feature extraction; Image recognition; Mars; Face detection; face-looking objects; pareidolia;
Conference_Titel :
Signal Processing and Communications Applications Conference (SIU), 2015 23th
Conference_Location :
Malatya
DOI :
10.1109/SIU.2015.7130307
