Perceptual Image Hashing Based on Three-Dimensional Global Features and Image Energy

In order to improve classification performance and operating efficiency of the hash algorithm, this paper proposes a novel algorithm that combines three-dimensional global features local energy features. During stage extraction, image is firstly compressed by SVD decomposition form secondary image. Then statistical at visual angle are extracted as Finally, feature generated using relationship between layers from different angles. extraction stage, luminance divided into blocks, then value each sub-block obtained. The multi-directional change taken Subsequent experimental results prove effectiveness proposed algorithm. not only has good robustness conventional content-preserving operations, but also achieves balance discrimination capability robustness. addition, compared with several state-of-the-art schemes, best ROC curve, shortest running time tamper detection ability.