Image Detection of GT Pesticide Test Kit Results in Organic Agricultural Products Us ing the CiRACORE Deep Learning Model
Year: 2024
Type: article
Abstract: This research aims to develop a modern and efficient tool for analyzing pesticide test results in organic agricultural products. This research uses 3,432 test tube images, divided into 3,120 training images and 312 testing images. The research steps are as follows: 1) Data collection: Test tube images were collected from testing of pesticides on organic agricultural produce. Each image has 3 or more test tubes. Each image has accompanying information, 2) AI system development: Use Deep Learning methods to develop an AI model for test tube image analysis, 3) AI system training: Train the AI model with a dataset of 2,746 test tube images, 4) Performance evaluation: Evaluate the performance. of the AI model with a test dataset of 686 images, 5) Results Analysis: Analyze the performance evaluation results of the AI model. From the analysis of the results, it was found that the AI model was effective in analyzing test tube images as follows: The average test tube accuracy was 92.48%. The average image accuracy was 92.62%. The AI system was able to correctly classify the test tubes. The AI system was able to quickly read the test results. This research demonstrates the potential of AI technology to be utilized in developing tools for analyzing pesticide test results, which will benefit farmers, consumers, and agencies responsible for detecting pesticide residues in agricultural products.
Author: Jantawong(Jearasuwan), Suwannee
Language: English
Topic: Smart Agriculture and AI
Subfield: Plant Science
Domain: Life Sciences
SDG: Zero hunger
Open Access status: diamond
OpenAlex ID: W7220511892