Optimization of a Similarity Performance on Bounded Content of Motion Histogram by Using Distributed Model

Autor:	Ouail Ouchetto, Abderrahmane Adoui El Ouadrhiri, Said Jai Andaloussi, El Mehdi Saoudi
Rok vydání:	2020
Předmět:	Similarity (geometry) Computer science business.industry Distributed element model computer.software_genre Image (mathematics) Histogram Bounded function Content (measure theory) Distributed data store Computer data storage Data mining business computer
Zdroj:	Advances on Smart and Soft Computing ISBN: 9789811560477
DOI:	10.1007/978-981-15-6048-4_1
Popis:	In this paper, a content-based video retrieval (CBVR) system called Bounded Coordinate of Motion Histogram version 2 (BCMH v2) was processed on a distributed computing platform by using Apache Hadoop framework and a real-time distributed storage system using HBase. In fact, the amount of multimedia data is growing exponentially. Most of this data is available in image and video models. Analyzing huge data involves complex algorithms, which leads to challenges in optimizing processing time and data storage capacity. Many content-based video retrieval systems are suitable for processing large video dataset, but they are limited by the computational time and/or storage on a single machine. Thus, this paper presents the effectiveness of the proposed method with the distributed computing platform and its evaluation on the HOLLYWOOD2 video dataset. The experimental results demonstrate the good performances of the proposed approach.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::dd1aaee6def31e7fa0805d871dec128d https://doi.org/10.1007/978-981-15-6048-4_1 Zobrazit plný text záznamu