ETRI-Knowledge Sharing Plaform

KOREAN
논문 검색
Type SCI
Year ~ Keyword

Detail

Conference Paper Block-based Masking Region Relocation and Detection Method for Image Privacy Masking
Cited 2 time in scopus Share share facebook twitter linkedin kakaostory
Authors
Sohee Park, Geonwoo Kim
Issue Date
2020-10
Citation
International Conference on Information and Communication Technology Convergence (ICTC) 2020, pp.1586-1588
Publisher
IEEE
Language
English
Type
Conference Paper
DOI
https://dx.doi.org/10.1109/ICTC49870.2020.9289372
Abstract
The widespread use of CCTV and various image devices has become a primary cause of privacy invasion, because these are possible to record, share and leak privacy images without owners' consent. The image privacy masking is one of technology for privacy prevention, and its necessity has been increased owing to need of personal information protection and social safety in these days [1]. In this paper, we propose a block-based masking region relocation and detection method to overcome the shortage of the meta-data typed privacy region information sharing method of restorable image masking service. This method is based on the histogram difference between the original image and the masked image. It analyzes the histogram feature of images, and relocates the masking region information from the coordinate system to the block system. Therefore, it set and detect the masking region without additional information such as meta-data and the original image. For demonstration the feasibility of our approach, we used the real-world database and the experimental results show the applicability of the real privacy masking service.
KSP Keywords
Coordinate system, Detection Method, Histogram difference, Histogram feature, Image masking, Image privacy, Information Sharing, Meta-data, Real-world, additional information, personal information protection