Title :
Iranian Face Database with age, pose and expression
Author :
Bastanfard, Azam ; Nik, Melika Abbasian ; Dehshibi, Mohammad Mahdi
Author_Institution :
Islamic Azad Univ., Karaj
Abstract :
This paper introduces a database of over 3,600 color images which we collected from 616 different human faces. It includes facial images of people between ages 2-85. Face images of persons with different ages is needed to generate a reliable age classification algorithm. Four different poses, two different expressions, and one image with glasses were taken if the subjects were interested. Information such as career, kind of skin, fingerprint, and cosmetic points (surgical points, fracture or laceration on face) is taken from participants. The background was a white frame and the only illumination was the daylight. We named this database the Iranian face database (IFDB). To evaluate the database the experimental result of a new feature detection algorithm is reported.
Keywords :
emotion recognition; face recognition; feature extraction; image colour analysis; lighting; pose estimation; visual databases; Iranian Face Database; age classification algorithm; facial images; feature detection algorithm; illumination; image color; Classification algorithms; Color; Engineering profession; Face detection; Fingerprint recognition; Glass; Humans; Image databases; Skin; Spatial databases; age classification; face image database; feature detection algorithm;
Conference_Titel :
Machine Vision, 2007. ICMV 2007. International Conference on
Conference_Location :
Islamabad
Print_ISBN :
978-1-4244-1624-0
Electronic_ISBN :
978-1-4244-1625-7
DOI :
10.1109/ICMV.2007.4469272