Improving Chili Pepper Seed Germination Rates through Deep Learning Using Macroscopic Images

• 발행기관: 한국컴퓨터게임학회
• 저자명: Soo-Kyung Moon Changyu-Ao Seung-Eon Jeong Dae-Won Park Youn-Mo Soung Man-Sung Kwen Uk Cho Dae-In Kang Sung-Ho Jung Gwang-Jun Kim
• 간행물 정보: 『한국컴퓨터게임학회논문지』제38권 1호, 106~115쪽, 전체 10쪽
• 주제분류: 공학 > 컴퓨터학
• 파일형태: PDF
• 발행일자: 2025.03.31

국문 초록

Germination of chili pepper seeds is critical for crop yield and resource utilization. A high germination rate increases yield and effectively reduces resource wastage. This study collected 450 macroscopic images of chili pepper seeds and constructed a dataset for deep learning training through standardized germination experiments. Six deep learning models were evaluated to improve the chili pepper seed classification accuracy and germination rate. After comparing the performance of the models, MobileNet_v2 performed the best, not only having the fewest number of parameters but also achieving a 98.89% accuracy and 97.82% F1 score. The model improved the original germination rate from 87.33% to 100% on the test set, significantly optimizing the seed selection process

목차

1. Introduction

2. Related Work

3. Materials and Methods

4. Results and Discussion

5. Conclusion And Future Work

참고문헌

키워드

Chili Pepper Seeds Germination Rate Macroscopic Images Deep Learning Convolutional Neural Networks