Improved SIFI algorithm for image tampering forensics

Abstract

The invention discloses an improved SIFI algorithm for image tampering forensics. The improved SIFI algorithm for the image tampering forensics improves: a) building an image scale space; b) positioning a feature point; c) forming feature vectors of the feature point; d) performing normalization processing on the feature vectors; e) serializing the feature vectors; f) judging tampering operation; g) judging the number of feature vector sets; h) equally dividing the feature vector sets; i) performing matching operation; j) highlighting image tampering positions. The improved SIFI algorithm for the image tampering forensics divides a round window which uses the feature point as the center and uses 4sigma as the radius into two concentric annuluses, respectively generates two 12 dimensional vectors in the central circle and the peripheral annulus so as to generate the feature vectors in 24 directions of the feature point, changes a prior mode of using 128 dimensional vectors, greatly reduces calculated amount of vector matching calculation, achieves high matching calculation efficiency of the feature vectors, and is suitable for tampering detection of a large number of pictures.

Description

technical field [0001] The present invention relates to an improved SIFT algorithm for image tampering and forensics, more specifically, it relates to a 24-dimensional vector formed by a central circle and a peripheral ring to replace the existing 128-dimensional vector to reduce the consumption of matching operations. An improved SIFT algorithm for image tampering forensics. Background technique [0002] The SIFT (Scale Invariant Feature Transform) algorithm is a scale-space-based image local feature description operator proposed by David G Lowe in 2004 that remains unchanged for image scaling, rotation, and even affine transformation. The SIFT feature matching algorithm has the characteristic of scale-invariant feature transformation, which can deal with the matching problems of translation, rotation, and affine transformation between two images, and has a strong matching ability. It has the strongest robustness and was mainly used for image recognition, image retrieval a...

AI Technical Summary

Problems solved by technology

like figure 1 As shown, a schematic diagram of the establishment of the DoG scale space in SIFT is given, figure 2 The schematic diagram of each feature point represented by a 128-dimensional vector is given. Since the 128-dimensional feature point description operator is used, 60% to 80% of the computing resources are spent on matching the 128-dimensional feature vectors. Its calculation efficiency is very low. If the number of images is large, it cannot meet the real-time requirements

Images