A cryptographic image encryption technique for facial-blurring of images
This addresses the need for secure facial protection in public media and social networks, particularly for sensitive cases like activism and abuse, though it appears incremental as it builds on existing encryption methods.
The paper tackles the problem of easily reversible facial blurring in images and videos by proposing an image encryption technique based on RGB pixel shuffling, which makes restoration difficult for off-the-shelf software while allowing law enforcement to reconstruct faces in abuse cases.
Protection of faces in pictures and videos of people in connection with sensitive information, activism, abused cases and others on public broadcasting media and social net- works is very important. On social networks like YouTube,facebook, Twitter and others, videos are being posted with blurring techniques of which some of them cannot be recoverable. Most blurring techniques used can easily be recoverable using off-the-shelf software. The ones that are difficult to be recovered also can easily be used by abusers and ther wrong doers. This paper proposes an image encryption technique that will make it possible for selected facial area to be encrypted based on RGB pixel shuffling of an m*n size image. This will make it difficult for off-the-shelf software to restore the ncrypted image and also make it easy for the law enforcement agencies to reconstruct the face back in case the picture or video is related to an abuse case. The implementation of the encryption method will be done using MATLAB. At the and, there will be no change in the total size of the image during encryption and decryption process.