Privacy Preserved Image Recognition on MSB Encrypted Images

Abstract: Cloud computing are the most valuable innovations for business, research, development, etc., providing cheap, virtual-services that will require expensive local hardware. With the availability of Cloud Computing we place almost everything in the cloud, but what do we really know about its security. One of the security risks in cloud computing according to Garfunkel is data intrusion. Privacy preservation of online data while offering efficient functionalities has become an important and focused research issue. Encryption is one of the fundamental techniques that manage the digital rights of any personal or other confidential information. In this paper we present a Privacy preserved image recognition system on MSB encrypted face images performed using one time padding, followed by Face image recognition with PCA-principal component analysis followed by SIFT- Scale invariant feature transform on selected images. MSB encryption provides protection of image with low PSNR from un-trusted managing authority cloud server. Whole face image recognition process performed in encrypted domain.

Keywords: Cloud; Face Images; PCA; PCA followed by SIFT; MSB; ROC;