All-Sky Cloud Classification Based on Transparency and Texture Features
This paper proposes a new algorithm to classify the cloud of all-sky ground-based based on transparency and texture features. First, we uses the transparency to separate the single sky background and cloud foreground image, which based on the natural matting of perceptual color space method, then analysis the texture features of cloud foreground image with second moment, contrast, correlation and entropy, finally, uses BP neural network to identify the type of the cloud. The experimental results show that the algorithm can separate the sky and cloud effectively, and the cloud classification recognition rate is higher.
X. Y. Chen et al., "All-Sky Cloud Classification Based on Transparency and Texture Features", Applied Mechanics and Materials, Vol. 235, pp. 3-8, 2012