Premium
Detection and Identification of Image Manipulation Based on Reversible Histogram Shift
Author(s) -
OBARA YUKI,
NIWA YUSUKE,
WADA SHIGEO
Publication year - 2017
Publication title -
electronics and communications in japan
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.131
H-Index - 13
eISSN - 1942-9541
pISSN - 1942-9533
DOI - 10.1002/ecj.11973
Subject(s) - histogram , artificial intelligence , computer vision , computer science , identification (biology) , process (computing) , image (mathematics) , pattern recognition (psychology) , fingerprint (computing) , botany , biology , operating system
SUMMARY Verification of image manipulation for various alterations is an indispensable technology to protect original images. Conventional forgery detection methods using fingerprint are useful, since the original image is not required in detection process. However, manipulated local region can't be specified. Further, type of manipulation is not identified. In this article, a novel forgery identification method based on reversible histogram shift is proposed. Our method can detect partial and overall manipulation regions and identify manipulation type. Simulation results are shown to demonstrate the effectiveness of our method using various types of manipulated database images.