SEIP： System for Efficient Image Processing on Distributed Platform

• Published in: Journal of computer science and technology Vol. 30; no. 6; pp. 1215 - 1232
• Main Author: 刘弢 刘轶 李钦 王香荣 高飞 朱延超 钱德沛
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.11.2015; Springer Nature B.V; School of Computer Science and Engineering, Beihang University, Beijing 100191, China
• Subjects: Accelerators; Algorithms; Artificial Intelligence; Batch processing; Big Data; Cloud computing; Computer Science; Data Structures and Information Theory; Feature extraction; Graphics processing units; Image processing; Image retrieval; Information Systems Applications (incl.Internet); Interfaces; Internet; Machine learning; Pipelining (computers); Platforms; Regular Paper; Small scale; Software Engineering; Theory of Computation; 分布式平台; 图像处理算法; 图像处理系统; 图像特征提取; 应用程序; 文件处理; 程序使用; 系统命名; image processing; distributed system; parallel programming framework; big data; GPU
• ISSN: 1000-9000; 1860-4749
• DOI: 10.1007/s11390-015-1595-1

Nowadays, there exist numerous images in the Internet, and with the development ot cloud compuung ano big data applications, many of those images need to be processed for different kinds of applications by using specific image processing algorithms. Meanwhile, there already exist many kinds of image processing algorithms and their variations, while new algorithms are still emerging. Consequently, an ongoing problem is how to improve the efficiency of massive image processing and support the integration of existing implementations of image processing algorithms into the systems. This paper proposes a distributed image processing system named SEIP, which is built on Hadoop, and employs extensible in- node architecture to support various kinds of image processing algorithms on distributed platforms with GPU accelerators. The system also uses a pipeline-based h＇amework to accelerate massive image file processing. A demonstration application for image feature extraction is designed. The system is evaluated in a small-scale Hadoop cluster with GPU accelerators, and the experimental results show the usability and efficiency of SEIP.