Chinese scientists have introduced a polygraph based on facial recognition technology and artificial intelligence (AI), which is expected to detect human lies more accurately.
Jointly developed by the Cloudwalk company under the Chongqing Institute of Chinese Academy of Sciences and Shanghai Jiao Tong University, the new type of polygraph was introduced earlier this week, after the release of the facial recognition system at the beginning of this month.
The polygraph can detect people's gender, tiny facial expressions, skin color, temperature, heart rate and voice characteristics through its camera and non-contact sensor. It can then analyze people's thoughts and mood based on the information collected, according to Zhou Xi, CEO of Cloudwalk company, and the head of the facial recognition project.
The core technology of the polygraph is called "AI brain." It includes six modules - facial recognition, voice recognition, semantic recognition, morphology recognition, physical recognition, and intelligence decision and control, Zhou said.
"Traditional polygraphs usually use a contact sensor to detect blood pressure, pause and muscle activities of the targets, but sometimes it doesn't work on people who have received professional training," Zhou said,"the advantage of our new polygraph is the non-contact detector, which will lower the vigilance of targets."
Compared with the traditional polygraph, the new model cost is quite high. The camera alone is worth about 500,000 yuan (77,200 U.S. dollars), but its advantage is obvious too, Zhang added.
"It can work in both daylight and dark environment, and offer more accurate test results," said Zhang.
According to the country's 13th Five-year Plan (2016-2020), the Ministry of Industry and Information Technology (MIIT) will make efforts to promote the development in advanced technologies like artificial intelligence, to guide the development of the electronics and information industry. (Xinhua)
86-10-68597521 (day)
86-10-68597289 (night)
86-10-68511095 (day)
86-10-68512458 (night)
cas_en@cas.cn
52 Sanlihe Rd., Xicheng District,
Beijing, China (100864)