期刊名称：International Journal of Innovative Research in Science, Engineering and Technology
印刷版ISSN：2347-6710
电子版ISSN：2319-8753
出版年度：2017
卷号：6
期号：9
页码：18086
DOI：10.15680/IJIRSET.2017.0609063
出版社：S&S Publications
摘要：Cloning is a common manipulation technique in image forgery. Cloning is the process of creating aforged image by copying a region of the image and pasting it into another region in the same image. A novel cloningdetection scheme using SLIC and MIFT is proposed. The proposed scheme combines block and keypoint-based cloningdetection methods. First, the host image segmented into non-overlapping and irregular blocks using Simple Lineariterative Clustering (SLIC). Second, block features are obtained from feature points of each block using Mirrorinvariant Feature Transform (MIFT), and then matched the block features with one another to locate the labeled featurepoints; this procedure can approximately indicate the suspected forgery regions. The forgery regions are detected moreaccurately by Forgery Region Extraction algorithm. It replaces the feature points with small super pixels as featureblocks. Merged regions are obtained by merging the neighboring similar local color feature blocks. Finally, amorphological process is applied on the merged regions to detect forgery regions.
关键词：Adaptive over-segmentation; Feature point matching; SLIC; Block features; MIFT; Forgery region;extraction algorithm; Super pixels; Local color features; Merged regions; Morphological operation.
