History of Facial Recognition Software
First semi-automated system
The first semi-automated facial recognition programs were created by Woody Bledsoe, Helen Chan Wolf, and Charles Bisson. Their programs required the administrator to locate features such as the eyes, ears, nose, and mouth on the photograph. It then calculated distances and ratios to a common reference point which was then compared to reference data.
Goldstein, Harmon, and Lesk
Used 21 specific subjective markers, such as hair color and lip thickness, to automate the recognition. The measurements and locations needed to be manually computed, causing the program to require a lot of labor time.
Kirby and Sirovich
Applied principle component analysis, a standard linear algebra technique, to the face recognition problem. Considered a milestone because it showed that less than one hundred values were required to accurately code a suitable aligned and normalized face.
Turk and Pentland
Discovered that while using the eigenfaces techniques, the residual error could be used to detect faces in images, a discovery that enabled reliable real-time automated face recognition systems. Although the approach was constrained by environmental factors, it created significant interest in furthering development of automated face recognition technologies.
The technology first captured the public’s attention from the media reaction to a trial implementation at the January 2001 Super Bowl, which captured surveillance images and compared them to a database of digital mugshots. It found 19 people with pending arrest warrants.
The Face Recognition Technology Evaluation (FERET) was sponsored by the Defense Advanced Research Products Agency (DARPA) from 1993 through 1997.
It encouraged the development of face recognition algorithms and technology by assessing the prototypes of face recognition systems. It propelled face recognition from its infancy to a market of commercial products.
The Face Recognition Vendor Tests (FRVT) were performed in 2000, 2002, and 2006. These evaluations built upon the work of FERET. The two goals were to assess the capabilities of commercially available facial recognition systems and to educate the public on how to properly present and analyze results.
FRVT 2002 was designed to measure technical progress since 2000, to evaluate performance on real-life large scale databases, and to introduce new experiments to help better understand face recognition performance.
The FRVT 2002 found that:
- Given reasonable controlled indoor lighting, the current state of the art in face recognition is 90% verification at a 1% false accept rate
- The use of morphable models, which maps a 2D image onto a 3D grid in an attempt to overcome lighting and pose variations, can significantly improve non-frontal face recognition.
- Watch list performance decreases as a function of gallery size – performance using smaller watch lists is better than performance using larger watch lists.
- In face recognition applications, accommodations should be made for demographic information since characteristics such as age and sex can significantly affect performance.
The Face Recognition Grand Challenge (FRGC) evaluated the latest face recognition algorithms available. High-resolution face images, 3D face scans, and iris images were used in the tests. The results indicated that the new algorithms are 10 times more accurate than the face recognition algorithms of 2002 and 100 times more accurate than those of 1995. Some of the algorithms were able to outperform human participants in recognizing faces and could uniquely identify identical twins.
Animetrics. (2008) Biometrics and facial recognition. Retrieved from http://www.animetrics.com/technology/frapplications.html
Blackburn, D. M., Bone, J. M. & Phillips, P. J. (2001). Facial recognition vendor test 2000 evaluation report. Retrieved from http://www.frvt.org
Goldstein, A. J., Harmon, L. D., & Lesk, A. B. (1971). Identification of human faces. Proceedings of the IEEE, 59(5), 748-760.
National Science and Technology Council. (2006). Face Recognition. Retrieved from http://www.biometrics.gov/Documents/FaceRec.pdf
Phillips, P. J. et al (2000). The FERET evaluation methodology for face-recognition algorithms. IEEE Transactions on PAMI, 22(10), 1090-1104. Retrieved from http://ieeexplore.ieee.org.ezproxy.umw.edu:2048/xpls/abs_all.jsp?arnumber=879790&tag=1
Sirovich, L. & Kirby, M. (1987). A low-dimensional procedure for the characterization of human faces. Journal of Optical Society of America, 4(3), 519-524. Retrieved from http://www-flare.cs.ucl.ac.uk/staff/S.Prince/4C75/Sirovich87.pdf
Turk, M. A. & Pentland, A. P. (1991). Face recognition using eigenfaces. Proceedings of the IEEE, 586-591. Retrieved from http://www.cs.tau.ac.il/~shekler/Seminar2007a/PCA%20and%20Eigenfaces/eigenfaces_cvpr.pdf