Toward Authentication of Videos: Integer Transform Based Motion Vector Watermarking

Abstract

Now a day, digital content like videos, audios and images are widely used as evidence in criminal courts and forensic labs. Due to advanced low-cost and easily available multimedia/communication tools and softwares, manipulation of the content is a no-brain task. Thus, the protection of digital content originality is a challenge for the content owners and researchers before it can be produced in court or used for some other purpose. In this paper, the motion vector watermarking technique has been proposed that validate/authenticate videos. We are embedding the correlated watermark in the integer wavelet transform domain and the selection of embedding areas is based on the variation of motion vectors. The video frames are fully protected in both spatial and transform domains since the watermark is correlated with the approximation subbands of wavelet transform before embedding. The proposed technique can concisely determine the attacked regions. The results validate the performance of the proposed approach in terms of quality metrics like peak signal to noise ratio (PSNR), structural similarity index (SSIM), normalized coefficients (NC) and bit error rate (BER).

Developments in Brain Tumor Segmentation Using MRI: Deep Learning Insights and Future Perspectives

“…Databases with complete details provide easy and quick access to specific and significant studies [29] [36]. Similarly, the pros and cons of overall categorized methods into thresholding, traditional machine learning, region-based, DL variants, and hybrid approaches can be found in [37] [161][162] [163]. Suppose the multi-scale information helps the network segment some easily confused areas at the edge of brain tumors.…”

Assessment of Cardiovascular Disease Using Machine Learning

“…Recent research has focused on utilizing various machine learning techniques to aid healthcare professionals in diagnosing heartrelated diseases [3]. This paper presents a survey that examines different models based on such methods and algorithms while evaluating their performance [4]. Among the researched models, those based on supervised learning algorithms such as Support Vector Machines (SVM), K-Nearest Neighbor (KNN), Naï ve Bayes, Decision Trees (DT), Random Forest (RF), and ensemble models have gained significant popularity.…”