STM Journals Peer-reviewed research from Consortium e-Learning Network

Journal of Multimedia Technology & Recent Advancements

Visual Duplicates in Video using Content based Analysis

  1. Neha Bhalerao
  2. Kavita Pandey
  3. Prachi Shinde
  4. Ashwini Magar

Abstract

This paper proposes a technique to detect visual duplicates in video using content-based analysis for analyzing duplicate videos in the database. Content-based analysis refers to analysis of digital media on the basis of features extracted from its contents. The proposed algorithm uses key frames, extracts spatial features and stores them in their respective feature vector. Feature vector stores the features extracted from key frame in numerical form. It then compares feature vectors from the database to that of the query video and displays whether the query video is duplicated or not. The authors have analyzed only a set of key frames instead of an entire video frame. Thus, it is memory-efficient to detect duplicated video when we handle a vast size of the videos.Keywords: visual duplicates, video, image, algorithm
Support