Computers can now guess our age

U.S. researchers have developed a software that can almost precisely guess your age. This software just needs a picture of your face to estimate your age. As said the project leader at the University of Illinois at Urbana-Champaign (UIUC), 'age-estimation software is useful in applications where you don't need to specifically identify someone.' This is not an easy task for a piece of software because the human aging process is determined not only by a person's genes, but also by many other factors including health, living style, living location, and even weather conditions. This new software could be used to 'stop underage drinkers from entering bars, prevent minors from purchasing tobacco products from vending machines, and deny children access to adult Web sites.' The computer scientists recognize that their software is not accurate enough today, but think it should be easy to improve it. Read more...

U.S. researchers have developed a software that can almost precisely guess your age. This software just needs a picture of your face to estimate your age. As said the project leader at the University of Illinois at Urbana-Champaign (UIUC), 'age-estimation software is useful in applications where you don't need to specifically identify someone.' This is not an easy task for a piece of software because the human aging process is determined not only by a person's genes, but also by many other factors including health, living style, living location, and even weather conditions. This new software could be used to 'stop underage drinkers from entering bars, prevent minors from purchasing tobacco products from vending machines, and deny children access to adult Web sites.' The computer scientists recognize that their software is not accurate enough today, but think it should be easy to improve it. Read more...

Human face aging process

You can see above the face aging process of two persons, Albert Einstein and Hillary Clinton, with each row describing these two famous people at different ages. (Credit: UIUC) This project has been led by Thomas Huang, professor of electrical and computer engineering at UIUC. He's also involved in several other institututions, including the Image Formation and Processing group at the university's Beckman Institute.

So is this software successful at guessing our age? "'Human faces do convey a significant amount of information, however, and provide important visual cues for estimating age,' Huang said. 'Facial attributes, such as expression, gender and ethnic origin, play a crucial role in our image analysis.' Consisting of three modules -- face detection, discriminative manifold learning, and multiple linear regression -- the researchers' age-estimation software was trained on a database containing photos of 1,600 faces. The software can estimate ages from 1 year to 93 years. The software's accuracy ranges from about 50 percent when estimating ages to within 5 years, to more than 80 percent when estimating ages to within 10 years. The accuracy can be improved by additional training on larger databases of faces, Huang said."

In the previous paragraph, Huang mentioned manifold learning. Here is a short explanation of what means manifold in this context. "A manifold is an abstract mathematical space in which every point has a neighborhood which resembles Euclidean space, but in which the global structure may be more complicated." (Source: Wikipedia).

The research team published several articles about this software approach. Here is the beginning of the abstract of an article published in IEEE Transactions on Multimedia, "Human Age Estimation With Regression on Discriminative Aging Manifold" (Volume 10, Issue 4, June 2008, Pages 578-584). "Recently, extensive studies on human faces in the human-computer interaction (HCI) field reveal significant potentials for designing automatic age estimation systems via face image analysis. The success of such research may bring in many innovative HCI tools used for the applications of human-centered multimedia communication. Due to the temporal property of age progression, face images with aging features may display some sequential patterns with low-dimensional distributions. In this paper, we demonstrate that such aging patterns can be effectively extracted from a discriminant subspace learning algorithm and visualized as distinct manifold structures."

You also can read an article published in IEEE Transactions onImage Processing, "Image-Based Human Age Estimation by Manifold Learning and Locally Adjusted Robust Regression" (Volume 17, Issue 7, Pages 1178-1188, July 2008). Here is the beginning of the abstract. "Estimating human age automatically via facial image analysis has lots of potential real-world applications, such as human computer interaction and multimedia communication. However, it is still a challenging problem for the existing computer vision systems to automatically and effectively estimate human ages. The aging process is determined by not only the person's gene, but also many external factors, such as health, living style, living location, and weather conditions. Males and females may also age differently. The current age estimation performance is still not good enough for practical use and more effort has to be put into this research direction."

Here is a link to the full paper (PDF format, 11 pages, 1.20 MB), from which the above illustration has been extracted.

If this subject interests you, another paper was presented at the Computer Vision and Pattern Recognition Workshop held in Anchorage, AK, in June 2008, "A Probabilistic Fusion Approach to Human Age Prediction." Here are two links to the abstract and to the full paper (PDF format, 6 pages, 194 KB), even if I'm not sure that this link will be valid permanently.

Sources: University of Illinois at Urbana-Champaign news release, September 23, 2008; and various websites

You'll find related stories by following the links below.