Processing Court Room Videos In Order To Improve Lie Detection

Lie Detection Software Learns from Real Court Cases

Humans were only accurate half the time, but the computer was up to 75 percent accurate.

Richard Lawler | December 12, 2015

Machine learning has been used to make computers guess your age, count calories and even do our jobs, but University of Michigan researchers are applying it to lie detection. In this case they used testimony from real court cases to try and decipher a liar's tells when the stakes are at their highest. Considering both the words and gestures of the person speaking, they claim it was up to 75 percent accurate at identifying if a person is lying or telling the truth, while humans could only tell 50 percent of the time.

Source: http://ns.umich.edu/new/releases/23356-lie-detecting-software-uses-real-court-case-data

<more at http://www.engadget.com/2015/12/12/lie-detection-software-learns-from-real-court-cases/; related links: http://www.engadget.com/2015/11/15/computer-detects-face-microexpressions/ (Computers learn how to spot hidden facial expressions. November 15, 2015) and http://ns.umich.edu/new/releases/23356-lie-detecting-software-uses-real-court-case-data (Lie-detecting software uses real court case data. December 10, 2015); further: http://www.telegraph.co.uk/news/science/science-news/12044093/How-to-spot-a-liar-its-not-what-you-think.html (How to spot a liar: it’s not what you think. If someone looks you in the eye and gives a straightforward answer, they may be lying, a new study suggests. December 10, 2015)>