Department of Electrical Engineering and Computer Science and School of Information, University of California, Berkeley, California 94705, USA; email:
Annu Rev Vis Sci. 2019 Sep 15;5:549-573. doi: 10.1146/annurev-vision-091718-014827.
From mainstream media outlets to social media and everything in between, doctored photographs are appearing with growing frequency and sophistication. The resulting lack of trust is impacting law enforcement, national security, the media, e-commerce, and more. While some types of manipulations can be detected with a careful visual examination, our visual system seems unable to reliably detect other types of manipulations. The field of image forensics has emerged to help return some trust in photography. I describe the perceptual limits of detecting manipulated images, as well as representative examples of computational techniques for authenticating images.
从主流媒体到社交媒体，再到其他各种渠道，经过篡改的照片越来越频繁地出现，而且手段也越来越高明。由此导致的信任缺失正在影响执法部门、国家安全、媒体、电子商务等诸多领域。虽然有些类型的篡改可以通过仔细的视觉检查来发现，但我们的视觉系统似乎无法可靠地检测到其他类型的篡改。图像取证领域的出现就是为了帮助恢复人们对摄影的一些信任。我描述了检测被篡改图像的感知限制，以及用于验证图像的计算技术的代表性示例。
Zotero 插件