Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Recurso digital |
| Language: | |
| Published: |
Zenodo
2025
|
| Online Access: | https://doi.org/10.5281/zenodo.15656180 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Table of Contents:
- <p><span>In India, Arecanut is often sorted by hand inspection techniques. This method is highly random, time-consuming, inefficient, and prone to making several errors. Arecanut exports have consequently sharply declined. As a result, an efficient system and technique for grouping Arecanut based on their size and textural properties must be developed. This can be accomplished using computer vision techniques. Computer vision is a fast, dependable, and unbiased inspection technique that has been adopted by many different types of enterprises. Because of its accuracy and speed, it aids in the creation of completely automated processes that satisfy ever-rising production and quality standards. For effective classification, a hybrid classification method that combines Support Vector Machine (SVM) and ResNet-extracted features is used. 98% accuracy, precision, F1-score, and recall are attained by the suggested system. These outcomes provide a more precise and automated Arecanut grading solution, outperforming conventional grading techniques by a wide margin. The sorting material, Arecanut, is delivered by conveyor belt, and a sensor detects it as it approaches the camera and signals the camera to take images of it. A host computer then receives the images and performs the necessary calculations and processes to automatically grade and sort the Arecanut as they go along the conveyor belt. </span></p> <p><strong><span>Keywords: </span></strong><span>Computer Vision, Arecanut, Automatic Grading, ResNet, Deep Learning (DL).</span></p>