Support vector machine-based approach for text description from the video

Abstract

Humans use communication, language either by written or spoken to describe the visual world around them. So, the study of text description for any video goes increasing. In this paper, we are representing a framework that gives output as a description for any long length video using natural language processing. The framework is divided into two sections called training and testing section. The training section is used to train the video with its description like activities of objects present in that video. This data is stored into the database with features of scenario of video. Another section is testing section. The testing section is used to test the video and retrieve the output as description of video comparing videos stored into database (i.e., in training section). Using NLP processing sentences are generated from objects and their activities. For the evaluation, a maximum of 50-second videos are used.