Efficient Privacy Preserving Viola-Jones Type Object Detection via Random Base Image Representation

Xin Jin 1 , Peng Yuan 1 , 2 , Xiaodong Li 1 , Chenggen Song 1 , Shiming Ge 3 , ∗ , Geng Zhao 1 , Yingya Chen 1

1 Beijing Electronic Science and Technology Institute, Beijing 100070, China

2 Xidian University, Xi’an 710071, China

3 Institute of Information Engineering, Chinese Academy of Sciences, Beijing 100095, China


    A cloud server spent a lot of time, energy and money to train a Viola-Jones type object detector [1] with high accuracy. Clients can upload their photos to the cloud server to find ob- jects. However, the client does not want the leakage of the content of his/her photos. In the meanwhile, the cloud server is also reluctant to leak any parameters of the trained object detectors. 10 years ago, Avidan & Butman introduced Blind Vision , which is a method for securely evaluating a Viola- Jones type object detector. Blind Vision uses standard cryp- tographic tools and is painfully slow to compute, taking a cou- ple of hours to scan a single image. The purpose of this work is to explore an efficient method that can speed up the process. We propose the Random Base Image (RBI) Representation . The original image is divided into random base images. Only the base images are submitted randomly to the cloud server. Thus, the content of the image can not be leaked. In the mean- while, a random vector and the secure Millionaire protocol are leveraged to protect the parameters of the trained object detector. The RBI makes the integral-image enable again for the great acceleration. The experimental results reveal that our method can retain the detection accuracy of that of the plain vision algorithm and is significantly faster than the tra- ditional blind vision, with only a very low probability of the information leakage theoretically.

Index Terms — Blind Vision, Random Base Image, Pri- vacy Preserving, Object Detection.




The proposed secure object classifier.  


, , , , , , :Efficient privacy preserving Viola-Jones type object detection via random base image representation. ICME : 673-678.



  author    = {Xin Jin and
               Peng Yuan and
               Xiaodong Li and
               Chenggen Song and
               Shiming Ge and
               Geng Zhao and
               Yingya Chen},
  title     = {Efficient privacy preserving Viola-Jones type object detection via
               random base image representation},
  booktitle = {2017 {IEEE} International Conference on Multimedia and Expo, {ICME}
               2017, Hong Kong, China, July 10-14, 2017},
  pages     = {673--678},
  year      = {2017},
  crossref  = {DBLP:conf/icmcs/2017},
  url       = {https://doi.org/10.1109/ICME.2017.8019497},
  doi       = {10.1109/ICME.2017.8019497},
  timestamp = {Thu, 07 Sep 2017 09:27:12 +0200},
  biburl    = {http://dblp.uni-trier.de/rec/bib/conf/icmcs/JinYLSGZC17},
  bibsource = {dblp computer science bibliography, http://dblp.org}


电子邮件地址不会被公开。 必填项已用*标注