Obfuscation of identifying features on patient videos and photos

患者视频和照片上识别特征的混淆

• 批准号: 485926-2015
• 负责人: Laganière, Robert
• 金额: $ 1.82万
• 依托单位: University of Ottawa
• 依托单位国家: 加拿大
• 项目类别: Engage Grants Program
• 财政年份: 2015
• 资助国家: 加拿大
• 起止时间: 2015-01-01 至 2016-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=585288
• 关键词: Obfuscation; identifying; features; patient; videos

The project consist in the development of a mobile applications that will have the ability to automatically detect identifying information such as faces, ears and tattoos in an image or a video. Once identified, the user is shown the region of interest to allow for an automated obfuscation algorithm to run so that the media can no longer be tied to an individual. The software solution will use a machine learning component trained to detect faces and possibly tatoos. The market for this application is every professional in the health sector who needs to share media between them in a secure manner.

该项目包括一个移动的应用程序的开发，将有能力自动检测识别信息，如面部，耳朵和纹身的图像或视频。一旦被识别，就向用户显示感兴趣的区域，以允许自动模糊算法运行，使得媒体不再与个人相关联。该软件解决方案将使用经过训练的机器学习组件来检测面部和可能的纹身。该应用程序的市场是卫生部门的每个专业人员，他们需要以安全的方式在他们之间共享媒体。