Video data image retrieval using – BRICH

Abstract

Purpose Data mining is the process of detecting knowledge from a given huge data set. Among the data set, multimedia is the data which contains diverse data such as audio, video, image, text and motion. In this growing field of video data, mining the video data plays vital role in the field of video data mining. In video data mining, video data are grouped into frames. In this vast amount of video frames, the fast retrieval of needed information is important one. This paper aims to propose a Birch-based clustering method for content-based image retrieval. Design/methodology/approach In image retrieval system, image segmentation plays a very important role. A text file, normally, is divided into sections, that is, piece, sentences, word and character for this information which are organized and indexed effectively like in a video, the information is dynamic in nature and this information is converted to static for easy retrieval. For this, video files are divided into a number of frames or segments. After the segmentation process, images are trained for retrieval process, and from these, unwanted images are removed from the data set. The noise or unwanted image removal pseudo-code is shown below. In the code image, pixel value represents the value of the difference between the two adjacent image pixel values. By assuming a threshold for the image value, the duplicate images are found. After finding the duplicate image, it is removed from the data set. Clustering is used in many applications as a stand-alone tool to get insight into data distribution and as a pre-processing step for other algorithms (Ester et al., 1996). Specifically, it is used in pattern recognition, spatial data analysis, image processing, economic science document classification, etc. Hierarchical clustering algorithms are classified as agglomerative or divisive. BRICH uses clustering attribute (CA) and clustering feature hierarchy (CA_Hierarchy) for the formation of clusters. It perform multidimensional data objects. Every BRICH algorithm based on the memory-oriented information, that is, memory constrains, is involved in the processing of the data sets. This information is represented in Figures 6-10. For forming clusters, they use the amount of object in the cluster (A), the sum of all points in the data set (S) and need the square value of the all objects (P). Findings The proposed technique brings an effective result for cluster formation. Originality/value BRICH uses a novel approach to model the degree of inter-connectivity and closeness between each pair of clusters that takes into account the internal characteristics of the clusters themselves.