easier to make.

　　With children, these aged images(图像) don't tend to resemble the older children, and matching photos of found children to old images in a database of missing children is difficult. "Given a recent face image of a child, it is extremely hard for a human to recognize, visually, who the child is from a large data set of child face images，" says Debayan Deb at Michigan State University.

　　Now Deb and his colleagues have created an algorithm(算法) to do this for them. They created a face­recognition algorithm on data sets, which contain images of nearly 1,000 children between 2 and 18 years old. Each was photographed at least four times over a period of six years.

　　AI learned to match recent photographs of children with images taken 2.5 years earlier 80 percent of the time.

　　With one year between the two photographs, the method was 90 percent accurate at recognizing faces. This dropped to 73 percent after three years. The approach beats comparing children with photos taken when they were aged 0 to 4 that have been aged by software, which stays at 50 percent recognition after six months. The new AI might help to improve accuracy of this kind of software as well.

　　Deb's next goal is to make the age gap wider. His team also hopes to develop an app that could be used to fight child trafficking.

　　语篇导读　本文主要介绍了人工智能能够确认失踪儿童的身份。

　　4．What is suggested in Para.1?

　　A．The old photos are hard to read.

　　B．Found children change greatly.

　　C．Children's faces are unpredictable.

　　D．Photos of children are easy to match.

　　解析 B　推理判断题。根据第一段第一句可知，随着失踪孩子年龄的增长，他们的长相和旧照片上的样子非常不同，即被找到的孩子变化很大，故选B项。

　　5．Why does Deb's team do the research?

　　A．To prove the advantages of AI function.

　　B．To help the police change their software.

　　C．To build a database to find the missing children.

　　D．To improve the accuracy of children's face­recognition.

解析 D　推理判断题。根据第三段中Deb所说的话和第四段第一句和第六段最后一句可知，Deb团队做研究的目的是提高儿童面部识别的准确性，故选D项。