Paper
24 August 2009 Super-cooled droplet splash image classification
Xueqing Zhang, Stuart Barnes, Shan Fu
Author Affiliations +
Proceedings Volume 7375, ICEM 2008: International Conference on Experimental Mechanics 2008; 73752F (2009) https://doi.org/10.1117/12.839215
Event: International Conference on Experimental Mechanics 2008 and Seventh Asian Conference on Experimental Mechanics, 2008, Nanjing, China
Abstract
It is proved that super-cooled large droplets (SLD) impingement onto airfoil have a great effect on aircraft icing. In the research facility of icing wind tunnel at Cranfield University in U.K, a great number of droplet splashing images are captured from aircraft icing experiments in order to understand the process of SLD impacting onto airfoil surfaces. Meanwhile, it also aims to classify the airfoil samples into wet/dry surface to determinate what material of samples is suitable for ice protection onto the aircraft. This paper defines a multi-dimensional feature space to characterize the images as criteria of classification. By k-means algorithm, images can be categorized into dry surface, wet surface, and ambiguous groups. Based on the results of image classification, eight of nine samples succeed to be identified into wet/dry behavior. However, one sample fell to the false identification since the raw images are insufficient to represent the entire droplets splash impact events.
© (2009) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Xueqing Zhang, Stuart Barnes, and Shan Fu "Super-cooled droplet splash image classification", Proc. SPIE 7375, ICEM 2008: International Conference on Experimental Mechanics 2008, 73752F (24 August 2009); https://doi.org/10.1117/12.839215
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Image classification

Diffusion

Image processing

Image analysis

Aerospace engineering

Clouds

Image display

Back to Top