Home // ALLSENSORS 2024, The Ninth International Conference on Advances in Sensors, Actuators, Metering and Sensing // View article

Dimensionality Reduction for CCD Sensor-Based Image to Control Fall Armyworm in Agriculture

Authors:
Alex Bertolla
Paulo Cruvinel

Keywords: CCD sensor, digital image, feature extraction, dimensionality reduction, principal component analysis.

Abstract:
Digital imaging sensors, such as Charge-Coupled Devices, have been used for large-scale agricultural pest control. The ability to process and analyze the amount of data generated by these sensors has become a challenge, especially due to the high dimensionality of the collected features. In the literature, it is possible to find various research on dimensionality reduction and algorithms. This article presents a study on the dimensionality re- duction of features from a digital image acquired with a Charge- Coupled Devices sensor in an agricultural field, in order to choose the optimal number of principal components for reducing feature dimensionality. In this context, it has become very important to define a method for selecting the optimal number of principal components for dimensionality reduction, while retaining only the necessary information associated with the main variables that describe the object of interest (Fall armyworms - Spodoptera frugiperda). The results showed, for example, that by using Hu invariant moments for feature extraction, dimensionality reduction was possible for all analyzed cases, leading to 80% of the original data. In this context, it was possible to preserve the semantic characteristics collected by the sensor and prepare them for classification.

Pages: 7 to 12

Copyright: Copyright (c) IARIA, 2024

Publication date: May 26, 2024

Published in: conference

ISSN: 2519-836X

ISBN: 978-1-68558-164-0

Location: Barcelona, Spain

Dates: from May 26, 2024 to May 30, 2024