Fast beta wavelet network-based feature extraction for image copy detection

The applications of authors' rights protection against illegal generation of images do not cease to evolve. However, most of them impose a very high computational cost especially when working with a database containing thousands of images. This paper addresses the problem of authors' rights violation and presents an original scheme, for Content-Based Image Copy Detection (CBICD), based on two screens: approximation screen and details screen. These two screens, based on Fast Beta Wavelet Transform (FBWT), aimed to filter the original images based first on their approximation and then on detail appearances respectively to display the corresponding original image to a given query one (a copy image). Extensive experiments of 8118 images from Copydays and Holidays datasets generated by INREA1 proved the effectiveness as well as the search speed of our approach in CBICD.