Design of Intelligent Insect Monitoring System Using Deep Learning Techniques

Sharmila, V.Ceronmani and Chauhan, Neeraj and Kumar, Rajdeep and Barwal, Suraj Kumar (2021) Design of Intelligent Insect Monitoring System Using Deep Learning Techniques. In: I3CAC 2021, 7-8 June 2021, Bharath University, Chennai, India.

[img]
Preview
Text (PDF)
eai.7-6-2021.2308788.pdf - Published Version

Download (916kB) | Preview

Abstract

The agriculture field is growing up its potential to better the demand of food and delivers healthy and nutritious foodstuff. This project presents an insect or pest detection and classification for the plant using machine learning. It’s a challenging part for the farmers to the crops which are acquiring defective and the degree or grade of excellence is also getting reduced day by day due to various pest or insect attacks. Earlier insect identification has been a big issue due to not well-skilled taxonomists to name the insects based on surface structure construction features accurately. Here, the proposed system will be a research tool for the study of early insects on the plants and leaves which will classify it using CNN and K-Means Clustering algorithm in machine learning. The detection analysis of insects was executed with shorter computational point in time for wang dataset using insect image Median Filter. The final classification results of accuracy were utilized to identify the pest and insects in the earliest period and increased the period to grow the harvest fertility and crop degree of excellence in the field of agriculture.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: insect or pest classification algorithm insect or pest detection algorithm machine learning cnn algorithm k-means clustering algorithm
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
QA75 Electronic computers. Computer science
Depositing User: EAI Editor IV
Date Deposited: 11 Jun 2021 08:03
Last Modified: 11 Jun 2021 08:03
URI: https://eprints.eudl.eu/id/eprint/3872

Actions (login required)

View Item View Item