A Deep Analysis of Image Based Video Searching Techniques

For many applications like brand monitoring, it’s important to search a video from large database using image as query[1]. Numerous visual search technologies have emerged with the passage of time such as image to video retrieval(I2V), video to video retrieval(V2V), color base video retrieval and image to image retrieval. Video searching in large libraries has become a new area of research. Because of advance in technology, there is a need of introducing the well established searching techniques for image base video retrieval task. The main purpose of this study is to find out the best image based video retieving technquie. This research shows the importance of image base video retrieving in the searching field and addresses the problem of selecting the most accurate I2V retrieval technique. A comparison of different searching techniques is presented with respect to some characteristics to analyze and furnish a decision regarding the best among them. The accuracy and retrieval time of different techniques is different. This research shows that there are a number of visual search techniques, all those techniques perform same function in different way with different accuracy and speed. This study shows that CNN is best as compare to others techniques. In future, the best among these techniques can be implemented to reduce the searching time and produce the promising result.