Deep Learning content-based search in media files (images and videos)

Abstract

The rapid growth of digital multimedia content has created a new demand for technologies that not only process but also sort and locate images and videos in the oceans of content. Generally, text-based traditional search engines are sometimes not able to retrieve specific visual content based on visual features, leading to technology development in computer vision for content-based image and video retrieval. This work presents the design, implementation, and evaluation of a user-friendly application, "Search by meaning and visual clues," that utilizes AI and YOLOv8 to offer users content-based search features. Our application allows users to probe multimedia sources using the image or video as input, which removes the laborious text-based queries. By employing modern computer vision, our application aims to produce prompt accurate search results with user friendliness being a top priority.