Authors :
Minzy M; Divya Mohan; Asha D.; V. Balamurugan; Aryamol S.
Volume/Issue :
Volume 9 - 2024, Issue 3 - March
Google Scholar :
https://tinyurl.com/49zccwcb
Scribd :
https://tinyurl.com/z464h5tt
DOI :
https://doi.org/10.38124/ijisrt/IJISRT24MAR1914
Abstract :
High resolution analysis of remote sensing images is
pivotal for various classification including land use
determination, environmental detection, environmental planning
and geospatial object recognition. This paper introduces a robust
method for categorizing satellite images into distinct groups,
facilitating accurate classification for global geographical areas.
It includes image compression, image preprocessing, image
segmentation and feature extraction. This innovative approach
enables precise identification and understanding of different
areas, contributing to optimize resource allocation and improved
land management practices in agriculture. CNN is the classifier
that is employed in this experiment. The outcome demonstrates
that our suggested strategy offers excellent accuracy,
outperforming many recently published publications.
Keywords :
CNN.
High resolution analysis of remote sensing images is
pivotal for various classification including land use
determination, environmental detection, environmental planning
and geospatial object recognition. This paper introduces a robust
method for categorizing satellite images into distinct groups,
facilitating accurate classification for global geographical areas.
It includes image compression, image preprocessing, image
segmentation and feature extraction. This innovative approach
enables precise identification and understanding of different
areas, contributing to optimize resource allocation and improved
land management practices in agriculture. CNN is the classifier
that is employed in this experiment. The outcome demonstrates
that our suggested strategy offers excellent accuracy,
outperforming many recently published publications.
