ISSN (Print): 2328-3491, ISSN (Online): 2328-3580, ISSN (CD-ROM): 2328-3629 American International Journal of Research in Science, Technology, Engineering & Mathematics AIJRSTEM 19-215; © 2019, AIJRSTEM All Rights Reserved Page 87 AIJRSTEM is a refereed, indexed, peer-reviewed, multidisciplinary and open access journal published by International Association of Scientific Innovation and Research (IASIR), USA (An Association Unifying the Sciences, Engineering, and Applied Research) Available online at http://www.iasir.net A Study on Hierarchical Clustering Algorithms 1 D.Saravanan, 2 Dr. Dennis Joseph Faculty of Operations & IT, ICFAI Business School (IBS), Hyderabad, The ICFAI Foundation for Higher Education (IFHE) (Deemed to be University u/s 3 of the UGC Act 1956) Hyderabad, India. 1. Introduction Techniques to understand digital video content becomes a hot research topic in recent years. Their main focus is on structure analysis [1], event detection [2], highlight summary [3], et al. As video contents normally take a long period of time to play and occupy a large volume of bytes to store, mining useful statistical information from the whole video content to help users have a better understanding of it is a relatively difficult task and has not been fully explored yet. Compared with object-, structure- or event-based video semantic information, statistical mining information is hard to be acquired by human labeling. Data mining is the process of finding useful patterns or extracting previously unknown knowledge from a massive set of data [4]. Different from textual information which has been studied for a long time, video contents have special characteristics: they are continuous sequences with temporal relations among them, and each video segment normally contains abundant information itself. Due to the semantic gap between human perception and computer-centered low-level features, many video understanding techniques such as shot boundary detection and event extraction remain open problems. Thus investigation on video mining is at its early stage as mining solutions normally need the extracted semantic information. In fact, the current status of video mining is still at the pre-processing stage, such as video clustering [5]. The main motivation of video mining is to find undiscovered knowledge from the stream based on visual and audio cues. The knowledge may typically include structure information within a video clip or association information among various clips, as well as trend information based on the analysis for a massive size of video set[7][8][9]. Clustering is an unsupervised machine learning process that creates clusters such that data points inside a cluster are close to each other, and also far apart from data points in other clusters. Clustering in data mining [SADC93, CHY96] is a discovery process that groups a set of data such that the intracluster similarity is maximized and the intercluster similarity is minimized [JD88, KR90, PAS96, CHY96]. Clustering is used in many applications, as a stand-alone tool to get insight into data distribution and as a preprocessing step for other algorithms. Specifically it is used in Pattern Recognition, Spatial Data Analysis, Image Processing, Economic Science, document classification etc. [10] II. Categories of clustering algorithms There are four main categories of clustering algorithms: partitioning, density-based, grid-based, and hierarchical. A. Clustering Approaches B. Partitioning algorithms Construct various partitions and then evaluate them by some criterion (k-means, k-medoids) C. Hierarchical algorithms Create a hierarchical decomposition of the set of data (or objects) using some criterion (AGNES, DIANA) D.Density-based Based on connectivity and density functions – grow a cluster as long as density in the neighborhood exceeds a threshold (DBSCAN, CLIQUE) E.Grid-based Abstract: Video Content is always huge by itself with abundant information. Extracting explicit semantic information has been extensively investigated such as object detection, structure analysis and event detection. However, little work has been devoted on the problem of discovering global or inexplicit information from the huge video stream. The video is a particular media embedding visual, motion, audio and textual information. The indexing process must be automated in order to build a dictionary of images region. This process is carried out in various steps. One such important step is Clustering, which is data mining is the process of discovering groups in a dataset. In this paper, we attempt to give a comparative study of existing algorithms suitable for video data mining. Keywords: Hierarchical, Clustering, Video data mining, Image Processing, Chameleon Algorithm.