Abstract
The data taken from the hyperspectral images are discrete and hard to classify because they are arranged in the contiguous spectral bands. We can easily detect and classify the data from the spectral images if the number of attributes in the images is very little. But it is very difficult to segregate the data from the images if the numbers of classes are more. To make the segregation easy we implement the procedure that utilizes a clustering algorithm. This paper comprises of two sections, firstly to perform unsupervised learning using different types of clustering algorithms and secondly, to compare the efficiency of the resultant clustering of these different methods to prove that which clustering method is best suitable in reading the hyperspectral imaging data. For this I have used these clustering algorithms, they are DBSCAN, MiniBatch K-Means, K-Means. By comparing these techniques I surmised that the K-Means is better for using the HyperSpectral Imaging data. To perform these calculations I used the Matlab data set from the Computational Intelligence Group.
Highlights
For the past decade, the geological survey has been done completely by humans
We planned to use the clustering algorithm because based on the data points that been distributed in the graph we can identify the exact shape of the image along with the clustering of the similar objects that provides the monochromatic output of the spectral image
This paper proposes the analysis of the performances of the three different clustering algorithms that are DBSCAN, MiniBatch K-Means, and K-Means, by utilizing the dataset provided by the CGI on the agricultural piece of land in Salinas valley in California
Summary
The geological survey has been done completely by humans It comprises of a lot of work including the surveying the whole land done by one team and collecting the data from them and separate and combine the identical classes by one team, and creating the raw map of the piece of land by another with all those details. It may even take more than 20 days for a single piece of land. With the help of the satellites, we can take the Hyperspectral images and with machine learning algorithms we can segregate the imaging data in a fraction of seconds
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call