男女羞羞视频在线观看,国产精品黄色免费,麻豆91在线视频,美女被羞羞免费软件下载,国产的一级片,亚洲熟色妇,天天操夜夜摸,一区二区三区在线电影
Global EditionASIA 中文雙語Fran?ais
Business

Masked faces pose no trouble to AI algos

By Fan Feifei and Du Juan | China Daily | Updated: 2020-02-26 00:00
Share
Share - WeChat

Artificial intelligence-powered technologies are increasingly being used to help contain the novel coronavirus outbreak in China, with several tech companies tweaking their facial recognition algorithms to identify people who are wearing masks.

Enterprises that use facial recognition for access control and attendance system needed to make the tweaks as traditional algorithms may not be sufficient for recognition. For, masks used by the employees often cover some features of the face.

Beijing-based tech company Hanwang Technology Co Ltd has upgraded its core algorithm and introduced a new facial recognition system for those who wear masks.

Huang Lei, vice-president of the company, said Hanwang Tech took just a month to develop the upgraded version. "We have rich experience in overseas markets for more than 10 years. In certain areas such as Africa and the Middle East, we have products that can recognize facial characteristics when the skin color or big beards pose difficulties," he said.

"We can quickly upgrade the existing products to recognize faces with masks," said Huang, adding that the upgrade often helps in accurate identification.

At present, the upgraded system has been deployed in the Bird's Nest stadium, Beijing No 3 Intermediate People's Court, Beijing Fire Museum and some other companies.

According to the government regulations about epidemic prevention and control, those who do not wear mask will be refused entry and alarms will be set off to remind the related authority on duty.

Internet, big data, AI and cloud computing should be deployed to prevent and control the epidemic, including the research of gene sequencing of the virus, tracking of patients, population flow and community management, said the Ministry of Industry and Information Technology.

Facial recognition has been one of the biggest emerging technologies over the past few years, as seen by its widespread use in everyday lives.

Yitu Technology, a Shanghai-based AI startup, has developed a contactless entrance guard system by applying facial recognition technology, which could identify each visitor within 300 milliseconds, with a 99.9-percent accuracy rate.

The company said the intelligent system can screen people even when they are wearing a mask. At present, it has been put into use in the headquarters of China Taiping Life Insurance, China CITIC Bank, the Shenzhen Civil Center, Baodi Square and other places.

SenseTime, another AI company that specializes in computer vision and deep learning, has launched a fever screening system, which could scan up to 10 people per second without direct contact and remotely identify individuals who display symptoms of a fever, lowering the risk of cross-infection and enhancing the speed for fever screening in crowded public places. The system integrates sophisticated AI algorithms with infrared thermal technology, and can also identify any individual without a face mask and send notification, with a success rate of over 99 percent.

Yu Xiaohui, deputy director of the China Academy of Information and Communications Technology said AI companies have given full play to their advantages, and released various AI-empowered solutions and products in a short period of time, making contributions in areas of epidemic monitoring, diagnosis and ensuring people's livelihoods.

"Some core AI technologies such as computer vision, natural language processing, robots and speech recognition have been widely used in the prevention and control of the outbreak," Yu said, adding AI is playing a positive role in helping enterprises resume production.

 

Today's Top News

Editor's picks

Most Viewed

Top
BACK TO THE TOP
English
Copyright 1994 - . All rights reserved. The content (including but not limited to text, photo, multimedia information, etc) published in this site belongs to China Daily Information Co (CDIC). Without written authorization from CDIC, such content shall not be republished or used in any form. Note: Browsers with 1024*768 or higher resolution are suggested for this site.
License for publishing multimedia online 0108263

Registration Number: 130349
FOLLOW US
主站蜘蛛池模板: 庐江县| 玛沁县| 湘阴县| 永顺县| 安吉县| 阳江市| 绥德县| 芦山县| 山东省| 怀仁县| 台东县| 乐昌市| 汨罗市| 古浪县| 大同县| 浦东新区| 高雄县| 措美县| 滦南县| 新沂市| 开平市| 赣榆县| 宾川县| 永清县| 盈江县| 阳曲县| 天台县| 福州市| 同心县| 贵阳市| 黎城县| 七台河市| 望奎县| 成武县| 武夷山市| 兖州市| 蕲春县| 盐城市| 营山县| 潞城市| 荥经县| 元阳县| 乌兰察布市| 泸水县| 成安县| 林西县| 景德镇市| 荥经县| 安西县| 绥江县| 定日县| 灵山县| 东乡县| 宣化县| 石门县| 永和县| 汉中市| 广州市| 密云县| 西平县| 礼泉县| 丰镇市| 衡山县| 临汾市| 石林| 长子县| 墨玉县| 久治县| 天峻县| 蒙山县| 洪泽县| 固原市| 铜鼓县| 沐川县| 永年县| 逊克县| 清新县| 庄浪县| 安化县| 额济纳旗| 驻马店市| 灵璧县|