Group items tagged

"The performance of LipNet compares incredibly favorably to human lipreading experts on GRID corpus, the largest publicly-available sentence-level lipreading dataset. In fact, where human experts got just 52 percent, LipNet scored 93 percent. Its sentence-based approach to lip-reading also smashed the best previous attempt by a machine, which managed 79.6 percent accuracy on the same dataset."

"built an algorithm that can determine with 90 percent accuracy whether a person is drunk or not based on an infrared image of his or her face."

"Neural networks can find telltale patterns in a person's gait that can be used to recognize and identify them with almost perfect accuracy, according to new research published in IEEE Transactions on Pattern Analysis and Machine Intelligence. The new system, called SfootBD, is nearly 380 times more accurate than previous methods, and it doesn't require a person to go barefoot in order to work. It's less invasive than other behavioral biometric verification systems, such as retinal scanners or fingerprinting, but its passive nature could make it a bigger privacy concern, since it could be used covertly."

"But its "surprising accuracy" was "very concerning". Questioned about this, he said that a database using facial recognition technology was unlikely to be a service that the company would create, but went on to say that "some company … is going to cross that line"."

"However, there is some concern about how accurate these new procedures will be. Apparently the facial recognition technology doesn't recognize all people will the same accuracy. White women and black people aren't as easily recognized as white men, meaning there could be some mismatching of identities. Some are also concerned that this is crossing the line in terms of passenger privacy."

"The algorithm, called Compas (Correctional Offender Management Profiling for Alternative Sanctions), is used throughout the US to weigh up whether defendants awaiting trial or sentencing are at too much risk of reoffending to be released on bail. Since being developed in 1998, the tool is reported to have been used to assess more than one million defendants. But a new paper has cast doubt on whether the software's predictions are sufficiently accurate to justify its use in potentially life-changing decisions."