A course-based age estimation system based on compute vision(openCV) and machine learning(CNN)
Dataset: Adience Benchmark Number of age labels: 8 (0, 2) (4, 6) (8, 12) (15, 20) (25, 32) (38, 43) (48, 53) (60-100)
Face Images, cropped and aligned 4000 as Training Set & 800 as Testing Set
Reference: [1] Paul Viola, Michael Jones. Rapid Object Detection using a Boosted Cascade of Simple Features. ACCEPTED CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION 2001
[2]Verónica Almeida et al. Automatic Age Detection based on Facial Images. IEEE 2ndInternational Conference on Communication, Control and Intelligent Systems (CCIS) , pp.110-114.
[3]Eran Eidinger, Roee Enbar, and Tal Hassner. Age and Gender Estimation of Unfiltered Faces. IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, VOL. 9, pp. 2170-2179
[4] Tianyue Zheng, Weihong Dengand Jiani Hu, "Age Estimation Guided Convolutional Neural Network for Age-Invariant Face Recognition," Computer Vision and Pattern Recognition Workshops (CVPRW),2017, pp. 503-511
[5]] Wojciech Samek, Alexander Binder and Sebastian Lapuschkin, "Understanding and Comparing Deep Neural Networks for Age and Gender Classification," Computer Vision Workshop (ICCVW), 2017, pp.1629-1638
[6]rude-carnie: age detection in tensorflow