A fast ELM-based machine compression scheme for underwater image transmission on a low-bandwidth acoustic channel. Issue 4 (19th June 2019)

• Record Type: Journal Article
• Authors: Zhang, Shujing; Zhang, Manyu; Cui, Yujie; Liu, Xingyue; He, Bo; Chen, Jiaxing
• Is Part Of: Sensor review. Volume 39:Issue 4(2019)
• Page Start: 542
• Page End: 553
• Publication Date: 2019-06-19
• Subjects: Extreme learning machine -- Image compression -- Principal components analysis; Sensor systems -- Periodicals; Detectors -- Industrial applications -- Periodicals; Engineering instruments -- Periodicals; 681.2
• DOI: 10.1108/SR-08-2018-0204
• Languages: English
• ISSNs: 0260-2288

Abstract

Abstract : Purpose: This paper aims to propose a fast machine compression scheme, which can solve the problem of low-bandwidth transmission for underwater images. Design/methodology/approach: This fast machine compression scheme mainly consists of three stages. Firstly, raw images are fed into the image pre-processing module, which is specially designed for underwater color images. Secondly, a divide-and-conquer (D&C) image compression framework is developed to divide the problem of image compression into a manageable size. And extreme learning machine (ELM) is introduced to substitute for principal component analysis (PCA), which is a traditional transform-based lossy compression algorithm. The execution time of ELM is very short, thus the authors can compress the images at a much faster speed. Finally, underwater color images can be recovered from the compressed images. Findings: Experiment results show that the proposed scheme can not only compress the images at a much faster speed but also maintain the acceptable perceptual quality of reconstructed images. Originality/value: This paper proposes a fast machine compression scheme, which combines the traditional PCA compression algorithm with the ELM algorithm. Moreover, a pre-processing module and a D&C image compression framework are specially designed for underwater images.