Adaptive hyper classification technique for satellite images

Abstract EN

The satellite image classification system intends to differentiate between the objects being present in the image.

It is highly challenging because the coverage area of the satellite is large such that the objects appear so small.

This makes the process of object differentiation complex.

Additionally, the classification accuracy is an important factor, which the classification system must pass through.

This work presents a satellite image classification system which can classify between the vegetation, soil and water bodies, etc.

Current research work is in the development of a hybrid classification technique for satellite images.

High-resolution satellite images that we deal with using SVM and low accuracy through the use of k-means.

It is necessary to provide accuracy and speed of satellite images and obtain this through the modulation method suggested through the integration of these technicians, where technology can classify all satellite images .We note that the proposed system is able to classify any satellite image by highlighting each region and what indicates that area and what percentage when applying the proposed system of classification whether the satellite images are based on high accuracy or low accuracy, where the system also shows the time taken to classify each satellite image.

We note that the time does not exceed 30 seconds for the number of images used within our database