ISSN(Online): 2319-8753 ISSN (Print): 2347-6710 International Journal of Innovative Research in Science, Engineering and Technology (A High Impact Factor, Monthly, Peer Reviewed Journal) Visit: www.ijirset.com Vol. 8, Issue 8, August 2019 Copyright to IJIRSET DOI:10.15680/IJIRSET.2019.0808072 8382 Semantic Concept Detection in Videousing MPEG Features Priya Kadam, Nita Patil, Sudhir Sawarkar Dept. of Computer Engineering, Datta Meghe College of Engineering Navi Mumbai, University of Mumbai, India Dept. of Computer Engineering, Datta Meghe College of Engineering Navi Mumbai, University of Mumbai, India Dept. of Computer Engineering, Datta Meghe College of Engineering Navi Mumbai, University of Mumbai, India ABSTRACT: The multimedia storage is increasing day by day. Also the cost to store these multimedia data is very less. Lots of videos available in the video warehouseare in unstructured format. As per user requirement, it is difficult to retrieve the relevant videos from such a huge video storage. Nowadays it is important to make such unstructured multimedia data easily available with flexibility. In recent years, lots of research is going on to extract the semantic concepts from multimedia data.The main purpose of concept detection is to provide semantic concept based retrieval of multimedia content. In previous content-based image and video retrieval systems, the retrieval was based on querying by examples and measuring the similarity of the database objects (images, video shots) with low-level features automatically extracted from the objects. The low-level features are insufficient to explain the content properly at conceptual level.The semantic gap characterizes the difference between two descriptions of an object by different linguistic representations, for instance languages or symbols. The semantic gap[14] can be defined as "the difference in meaning between constructs formed within different representation systems". This “semantic gap” isbasic problem in content-based multimedia retrieval system. The main aim is to form semantic representations by extracting intermediate semantic levels (events, objects, locations, people, etc.) from low-level visual and audio features by using machine learning algorithms. In recent studies it is observed that the accuracy of the concept detector is far from perfection but still those detectors can be useful in high- level indexing and querying on multimedia data. This is possible because semantic concept detectors can be trained off- line with supervised learning algorithms and with positive and negative training examples which are available at query time. Here, we are mentioned the description of our proposed system and its methodology for implementation of semantic concept detection. The main aim of this system is to improve the accuracy of concept detection. KEYWORDS: Shot detection,Key frame extraction,Support vector machine;Concept Detection,Concept Correlation. I. INTRODUCTION In image processing, to detect high-level concepts within multimedia documents is the big problem.Lots of research is going on as amount of audiovisual content is increasing day by day and nowadays this is interest area for many researchers. The focus set mainly on the extraction of various low-level features i.e.audio, color, texture and shape properties of audiovisual content. Lot of new techniques such as neural networks, fuzzy logic systems and Support Vector Machines (SVM) used to find out high-level features from low level features. Lots of frameworks are already developed and every framework has their own result and accuracies. Here, purpose is to develop a system for concept detection with better accuracy. General framework for video concept detection is shown in figure 1. Shot detection is the initial step in concept detection framework. It used to detect transition between successive shots.Key frame extraction plays a vital role to analyze the video content and its management. Key frame extraction gives the summary to retrieve video.A video shot