Bài báo “Applying Machine Learning for Chili Pepper Phenotyping and Feature Extraction”
Link bài báo: https://doi.org/10.1016/j.atech.2025.101458
Sinh viên thực hiện:
• Hà Trọng Tài – KHTN2021 – Tác giả chính
• Phạm Thị Nga – KHMT2021 – Đồng tác giả
Hướng dẫn khoa học:
• TS. Mai Tiến Dũng
• TS. Thái Thanh Tuấn
Tóm tắt nghiên cứu:
Accurate characterization of chili pepper morphology is essential for breeding programs and genetic studies. Traditional phenotyping approaches are often constrained by small sample sizes and a limited set of measurable traits, restricting comprehensive analysis.
In this study, we present an automated, image-based phenotyping framework that leverages computer vision and machine learning to extract detailed morphological features from longitudinal slice images of chili peppers.
To accurately detect chili fruits and their seeds, the framework employs the YOLOv7 object detection model, achieving a precision of 0.92 and a mean Average Precision (mAP) of 0.87. Building upon these detections, we apply advanced image processing techniques to quantify key phenotypic traits, including seed count, fruit color intensity, length, width, surface area, and surface wrinkle characteristics.
These parameters provide critical insights for variety classification, breeding selection, and genetic resource management. The proposed methodology not only enables scalable and reproducible phenotypic assessment but also establishes a searchable dataset of chili pepper varieties, thereby enhancing the efficiency, accuracy, and analytical depth of chili pepper research and breeding programs.
"Chúng em xin gửi lời tri ân đặc biệt đến thầy TS. Mai Tiến Dũng và thầy TS. Thái Thanh Tuấn vì sự hướng dẫn tận tâm, kiên nhẫn và đầy trách nhiệm trong suốt quá trình nghiên cứu. Chính sự chỉ dẫn quý báu cùng những góp ý sâu sắc của các thầy đã giúp chúng em định hướng đúng đắn, phát triển tư duy khoa học và hoàn thiện đề tài. Chúng em vô cùng trân trọng những nỗ lực và tình cảm mà các thầy đã dành cho chúng em, coi đó là hành trang quý giá cho con đường học tập và nghiên cứu sau này."
JOURNAL – SMART AGRICULTURAL TECHNOLOGY (ELSEVIER):
Smart Agricultural Technology is an international open-access journal, serving as a companion to the reputable Computers and Electronics in Agriculture.
It focuses on practical applications of smart technologies — including AI, IoT, robotics, imaging, and sensors — for agricultural production across agronomy, horticulture, forestry, aquaculture, and livestock.
The journal emphasizes real-world deployment such as soil and crop management, seeding, harvesting, pest detection, animal welfare, and farm product quality assessment.
It is indexed in Scopus and ranked Q1 in Agricultural Engineering and related fields, with an Impact Factor of 5.7 and a CiteScore of 7.7, making it a high-impact and reputable publication in smart agriculture research.
Thông tin chi tiết: https://www.facebook.com/UIT.Fanpage/posts/pfbid0e5mkvLW8z7T6txQe5VnFpJLh29DjMb6NJimK6G4HSZHw8GB7S27fRkQ34pFAZQ27l
