Cloud Classification Using Ground Based Images Using CBIR and K-Means Clustering

Artificial Intelligence (AI) and especially Machine learning (ML) is finding to be useful in many tasks that are simple to carryout to complex tasks that are found to be challenging in nature. One such application of ML is in classification of images. In this paper an attempt to blend the application of unsupervised ML (k-means clustering) approach along with content based image retrieval (CBIR) approach is presented to classify clouds. K-means is a simple approach which can be applied for image classification, also k-means easily adapts to new examples of classification. An attempt is made to combine the features of k-means and CBIR to classify the cloud images. It is performing a double check on the cloud image being classified. Clustering in included with CBIR to obtain an easy retrieval of cloud image. Three categories are chosen for classification - low level clouds, high level clouds and medium level clouds. The classification of clouds is achieved with the help of ground based images (or whole sky images). High resolution of ground based images can be obtained with the help of new high resolution cameras. These ground based images are processed to classify the clouds present in the images into the three categories as mentioned above. Ground based images captured by ground based cameras provide better ground truth. The results find its application in various domains such as agriculture, aviation, military, and various meteorological applications.