Image Splicing Localization Using Superpixel Segmentation and Noise Level Estimation
Siqian Li, Weimin Wei, Xiuru Hua, Xueling Chu · 2019
With the development of computer and artificial intelligence technology, the authenticity of digital images has been seriously challenged. How to judge the authenticity of digital images has become an important research direction. At present, splicing is one of the most common image tampered methods. Different sources of images have different noise levels, and this paper proposes a scheme to locate the image splicing areas by detecting the inconsistency of the local noise level of the image. Firstly, the image to be detected is segmented into pixel blocks with similar features by using SLIC (Simple Linear Iterative Clustering) superpixel segmentation algorithm. Secondly, the noise level estimation method based on PCA (Principal Component Analysis) is used to calculate the local noise level of each image block. Finally, using three clustering algorithms to cluster the results of the estimated noise level, and the splicing areas of the image is located according to the clustering results. The results show that the proposed scheme in this paper can effectively locate the splicing areas and retain more edge information of the detected areas.