JKAU: Comp. IT. Sci., Vol. 8 No. 2, pp: 33 – 45 (1440 A.H. / 2019 A.D.) Doi: 10.4197/Comp. 8-2.3 33 Video Watermarking for Copyright Protection with Genetic-Based Frame Selection Saud S. Alotaibi Department of Information Systems, College of Computer and Information Systems, Umm Al Qura University, Makkah, Saudi Arabia ssotaibi@uqu.edu.sa Abstract . Recently, video watermarking has received much consideration. Several applications in a variety of domains have been implemented, and many are progressing. This paper intends to formulate a novel video watermarking framework that includes three stages: (i) Optimal video frame prediction, (ii) A watermark embedding process, and (iii) A watermark extraction process. In the proposed model, the optimal frame prediction is carried out using the deep belief network (DBN) framework. Initially, randomly chosen frames from each video are used as the input to a genetic algorithm (GA) model that optimally chooses the frames such that the peak signal-to- noise ratio (PSNR) should be maximal. The frames are assigned with a label of one or zero, where a label of one denotes a frame with better PSNR (can select for embedding process) and a label of zero denotes the frame with reduced PSNR (cannot be used for embedding). Consequently, a data library is formed from the obtained results, where each video frame is determined with their gray- level cooccurrence matrix (GLCM) features and labels (can embed or not), which is then trained in the DBN framework, from which the optimal frames can be predicted efficiently while testing. Furthermore, the watermark embedding process and watermark extraction process are carried out, and thus, the image can be embedded within the optimally selected frames. Keywords: Video watermarking, Genetic algorithm, GLCM features, Deep belief network, Error measures. Abbreviations DBN Deep Belief Network GA Genetic Algorithm PSNR Peak Signal-to-Noise Ratio GLCM Gray-Level Cooccurrence Matrix IPR Intellectual Property Rights DWT Discrete Wavelet Transform BWT Biorthogonal Wavelet Transform ABC Artificial Bee Colony SIFT Scale Invariant Feature Transform BE Blind Extraction HEVC High-Efficiency Video Coding VBR Video Bit Rate MSE Mean Squared Error LSB Least Significant Bit SDME Second Derivative-like Measure of Enhancement 1. Introduction In recent years, the privacy of important documents has become essential. In the fast- growing computer environment, maintaining the secrecy of soft copies of medical records is a major challenge and becomes even more difficult in hospitals as the number of patients increases [1-3] . Hence, a proper and suitable application is essential to secure the required data. Watermarking has attracted considerable attention recently [4-6] , and it provides protection to digital content and conserves the