题目

阅读下列短文，选出最佳选项。 It's possible that your phone's face-unlock might finally be able to work while you're wearing a mask. Researchers have found that facial recognition algorithms (算法) are getting better at recognizing faces in masks, according to data published on Tuesday by the National Institute for Standards and Technology (NIST). Using independent testing of more than 150 separate facial recognition algorithms, the new report suggests masks may not be as big a problem for facial recognition systems as initially thought. When NIST first examined masks' effect on facial recognition in July 2020, it found that algorithms weren't great at identifying faces with masks. "Face recognition can make errors, which can implicate people for crimes they haven't committed," writes the Electronic Frontier Foundation (EFF). "It is particularly bad at recognizing African Americans and other ethnic minorities, women, and young people." But the pandemic has given developers plenty of time to focus on the mask problem, and NIST's data shows that facial recognition algorithms are getting better at working with masked faces. "After the pandemic, some developers have submitted algorithms which show significantly improved accuracy and are now among the most accurate in our test," the report reads. NIST's public ranking for facial recognition tests bears out this report. Eight different algorithms now hold false rates below 0.05 percent. Nevertheless, there remain a number of limitations to the study. NIST researchers did not employ actual images of masked faces. Instead, they applied masks digitally to ensure consistency across the sample. As a result, "We were not able to get a thorough simulation (模仿) of the endless variations in color, design, shape, texture, and ways masks can be worn," the report states. The digital mask was a blue surgical mask covering the full width of the face, but testers noted that performance varied considerably depending on how high the mask was placed on the face. （1） Recognizing masked faces with facial recognition systems used to be thought as _______. A . effective B . impossible C . easy D . challenging （2） What does the underlined phrase "bear out" in Paragraph 3 mean? A . Make. B . Prove. C . Deny. D . Oppose. （3） What can be learned about the study? A . The way to wear masks may affect recognition accuracy. B . The design of a mask makes no difference to facial recognition. C . Facial recognition failure rates were quite low at the beginning. D . The researchers adopted real surgical masks to ensure the accuracy. （4） Which of the following is a suitable title for the text? A . Limitations of Facial Recognition Software B . The Challenge of Recognizing Masked Faces C . The improvement in Facial Recognition Algorithms D . Different Applications of Facial Recognition Technology 答案： D B A C

查看本题答案和解析