Comparing Linear Discriminant Analysis to AlexNet as a Novel Approach for Better Remote Sensing Image Segmentation and Classification with Improved Accuracy

Abstract

Aim: Analyzing and categorizing individual items in images is part of image classification. Our major goal is to compare the performance of two different types of image segmentation classifiers which are used in the image segmentation process. The image segmentation is applied in many sectors, such as flood detection and evaluation, agricultural monitoring, environmental monitoring, defense, and so on. The classification and segmentation of small regions of interest from ground photographs is critical. One image of every location is randomly selected and changed into the bitmap formation to create the test type dataset consisting of 5 locations from the 400 different satellite images. Total 10 numbers of iterations were computed with400 images which were collected from 5 various locations. The images were collected at different views.Materials and Methods: The classifiers are making use to segment the remote sensor images using the AlexNet framework and LDA (Linear Discriminant Analysis). In this research work, The ORL kind image database is used for analysis, and the implementation is processed with the assistance of Python programming. Results and Discussion: The outcome of novel AlexNet compared with Linear Discriminant Analysis, which has an accuracy of 95.80%, the classifier accuracy confirmed with 93.70%. The two algorithms are statistically satisfied with the independent sample t-Test two tailed is 0.422 (