How old do you think your computer is? Computer age categorization for security, custody and surveillance – sciencedaily


Computerized facial recognition is an important part of initiatives to develop security systems, create social networks, preserve photographs and many other applications. Systems that allow a computer to accurately estimate a person’s age based on an analysis of their face are discussed in the International Journal of Applied Pattern Recognition.

Jayant Jagtap and Manesh Kokare of the Department of Electronic Engineering and Telecommunications, at the Shri Guru Gobind Singhji Institute of Engineering and Technology, in Vishnupuri, Nanded, India, suggest that age classification adds a useful layer to these systems of security, management. for customer relations, and of course for monitoring. The team conducted a detailed survey of age classification systems to reveal the pros and cons of each and to point further research in the right direction for the development of an algorithm that is even more accurate than anything in existence today. . Indeed, their investigation reveals that despite the best efforts of the developers, there is not yet a very precise real-time algorithm for age classification. Existing age classification systems commonly use geometric ratios of facial features and analysis of skin wrinkles.

One of the problems faced by the developers of such a tool is that databases with images of a person’s face tend not to accumulate images at different ages. This limits the quality of learning an algorithm based on a database of photos at known ages. While there are many serious tools and many deceptive or funny tools available on the internet, there is no public system that allows a computer to guess your age with useful accuracy. This might just be a positive point to make from a privacy perspective, but not for the broader implications of facial recognition and age categorization.

Source of the story:

Material provided by Inderscience Publishers. Note: Content can be changed for style and length.


Comments are closed.