AI-powered detection and quantification of Post-harvest Physiological Deterioration (PPD) in cassava using YOLO foundation models and K-means clustering
Post-harvest physiological deterioration (PPD) poses a significant challenge to the cassava industry, leading to substantial economic losses. This study aims to address this issue by developing a comprehensive framework in collaboration with cassava breeders. Advanced deep learning (DL) techniques s...
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Journal Article |
| Lenguaje: | Inglés |
| Publicado: |
BioMed Central
2024
|
| Materias: | |
| Acceso en línea: | https://hdl.handle.net/10568/162791 |
| _version_ | 1855522933768716288 |
|---|---|
| author | Gomez Ayalde, Daniela Giraldo Londono, Juan Camilo Quiroga Mosquera, Audberto Luna-Melendez, Jorge Luis Gimode, Winnie Tran, Thierry Zhang, Xiaofei Selvaraj, Michael Gomez |
| author_browse | Gimode, Winnie Giraldo Londono, Juan Camilo Gomez Ayalde, Daniela Luna-Melendez, Jorge Luis Quiroga Mosquera, Audberto Selvaraj, Michael Gomez Tran, Thierry Zhang, Xiaofei |
| author_facet | Gomez Ayalde, Daniela Giraldo Londono, Juan Camilo Quiroga Mosquera, Audberto Luna-Melendez, Jorge Luis Gimode, Winnie Tran, Thierry Zhang, Xiaofei Selvaraj, Michael Gomez |
| author_sort | Gomez Ayalde, Daniela |
| collection | Repository of Agricultural Research Outputs (CGSpace) |
| description | Post-harvest physiological deterioration (PPD) poses a significant challenge to the cassava industry, leading to substantial economic losses. This study aims to address this issue by developing a comprehensive framework in collaboration with cassava breeders. Advanced deep learning (DL) techniques such as Segment Anything Model (SAM) and YOLO foundation models (YOLOv7, YOLOv8, YOLOv9, and YOLO-NAS), were used to accurately categorize PPD severity from RGB images captured by cameras or cell phones. YOLOv8 achieved the highest overall mean Average Precision (mAP) of 80.4%, demonstrating superior performance in detecting and classifying different PPD levels across all three models. Although YOLO-NAS had some instability during training, it demonstrated stronger performance in detecting the PPD_0 class, with a mAP of 91.3%. YOLOv7 exhibited the lowest performance across all classes, with an overall mAP of 75.5%. Despite challenges with similar color intensities in the image data, the combination of SAM, image processing techniques such as RGB color filtering, and machine learning (ML) algorithms was effective in removing yellow and gray color sections, significantly reducing the Mean Absolute Error (MAE) in PPD estimation from 20.01 to 15.50. Moreover, Artificial Intelligence (AI)-based algorithms allow for efficient analysis of large datasets, enabling rapid screening of cassava roots for PPD symptoms. This approach is much faster and more streamlined compared to the labor-intensive and time-consuming manual visual scoring methods. These results highlight the significant advancements in PPD detection and quantification in cassava samples using cutting-edge AI techniques. The integration of YOLO foundation models, alongside SAM and image processing methods, has demonstrated promising precision even in scenarios where experts struggle to differentiate closely related classes. This AI-powered model not only effectively streamlines the PPD assessment in the pre-breeding pipeline but also enhances the overall effectiveness of cassava breeding programs, facilitating the selection of PPD-resistant varieties through controlled screening. By improving the precision of PPD assessments, this research contributes to the broader goal of enhancing cassava productivity, quality, and resilience, ultimately supporting global food security efforts. |
| format | Journal Article |
| id | CGSpace162791 |
| institution | CGIAR Consortium |
| language | Inglés |
| publishDate | 2024 |
| publishDateRange | 2024 |
| publishDateSort | 2024 |
| publisher | BioMed Central |
| publisherStr | BioMed Central |
| record_format | dspace |
| spelling | CGSpace1627912025-11-11T18:46:50Z AI-powered detection and quantification of Post-harvest Physiological Deterioration (PPD) in cassava using YOLO foundation models and K-means clustering Gomez Ayalde, Daniela Giraldo Londono, Juan Camilo Quiroga Mosquera, Audberto Luna-Melendez, Jorge Luis Gimode, Winnie Tran, Thierry Zhang, Xiaofei Selvaraj, Michael Gomez agricultural practices cassava breeding Post-harvest physiological deterioration (PPD) poses a significant challenge to the cassava industry, leading to substantial economic losses. This study aims to address this issue by developing a comprehensive framework in collaboration with cassava breeders. Advanced deep learning (DL) techniques such as Segment Anything Model (SAM) and YOLO foundation models (YOLOv7, YOLOv8, YOLOv9, and YOLO-NAS), were used to accurately categorize PPD severity from RGB images captured by cameras or cell phones. YOLOv8 achieved the highest overall mean Average Precision (mAP) of 80.4%, demonstrating superior performance in detecting and classifying different PPD levels across all three models. Although YOLO-NAS had some instability during training, it demonstrated stronger performance in detecting the PPD_0 class, with a mAP of 91.3%. YOLOv7 exhibited the lowest performance across all classes, with an overall mAP of 75.5%. Despite challenges with similar color intensities in the image data, the combination of SAM, image processing techniques such as RGB color filtering, and machine learning (ML) algorithms was effective in removing yellow and gray color sections, significantly reducing the Mean Absolute Error (MAE) in PPD estimation from 20.01 to 15.50. Moreover, Artificial Intelligence (AI)-based algorithms allow for efficient analysis of large datasets, enabling rapid screening of cassava roots for PPD symptoms. This approach is much faster and more streamlined compared to the labor-intensive and time-consuming manual visual scoring methods. These results highlight the significant advancements in PPD detection and quantification in cassava samples using cutting-edge AI techniques. The integration of YOLO foundation models, alongside SAM and image processing methods, has demonstrated promising precision even in scenarios where experts struggle to differentiate closely related classes. This AI-powered model not only effectively streamlines the PPD assessment in the pre-breeding pipeline but also enhances the overall effectiveness of cassava breeding programs, facilitating the selection of PPD-resistant varieties through controlled screening. By improving the precision of PPD assessments, this research contributes to the broader goal of enhancing cassava productivity, quality, and resilience, ultimately supporting global food security efforts. 2024-11-23 2024-11-27T10:00:27Z 2024-11-27T10:00:27Z Journal Article https://hdl.handle.net/10568/162791 en Open Access application/pdf BioMed Central Gomez Ayalde, D.; Giraldo Londono, J.C.; Quiroga Mosquera, A.; Luna-Melendez, J.L.; Gimode, W.; Tran, T.; Zhang, X.; Selvaraj, M.G. (2024) AI-powered detection and quantification of Post-harvest Physiological Deterioration (PPD) in cassava using YOLO foundation models and K-means clustering. Plant Methods 20: 178 . ISSN: 1746-4811 |
| spellingShingle | agricultural practices cassava breeding Gomez Ayalde, Daniela Giraldo Londono, Juan Camilo Quiroga Mosquera, Audberto Luna-Melendez, Jorge Luis Gimode, Winnie Tran, Thierry Zhang, Xiaofei Selvaraj, Michael Gomez AI-powered detection and quantification of Post-harvest Physiological Deterioration (PPD) in cassava using YOLO foundation models and K-means clustering |
| title | AI-powered detection and quantification of Post-harvest Physiological Deterioration (PPD) in cassava using YOLO foundation models and K-means clustering |
| title_full | AI-powered detection and quantification of Post-harvest Physiological Deterioration (PPD) in cassava using YOLO foundation models and K-means clustering |
| title_fullStr | AI-powered detection and quantification of Post-harvest Physiological Deterioration (PPD) in cassava using YOLO foundation models and K-means clustering |
| title_full_unstemmed | AI-powered detection and quantification of Post-harvest Physiological Deterioration (PPD) in cassava using YOLO foundation models and K-means clustering |
| title_short | AI-powered detection and quantification of Post-harvest Physiological Deterioration (PPD) in cassava using YOLO foundation models and K-means clustering |
| title_sort | ai powered detection and quantification of post harvest physiological deterioration ppd in cassava using yolo foundation models and k means clustering |
| topic | agricultural practices cassava breeding |
| url | https://hdl.handle.net/10568/162791 |
| work_keys_str_mv | AT gomezayaldedaniela aipowereddetectionandquantificationofpostharvestphysiologicaldeteriorationppdincassavausingyolofoundationmodelsandkmeansclustering AT giraldolondonojuancamilo aipowereddetectionandquantificationofpostharvestphysiologicaldeteriorationppdincassavausingyolofoundationmodelsandkmeansclustering AT quirogamosqueraaudberto aipowereddetectionandquantificationofpostharvestphysiologicaldeteriorationppdincassavausingyolofoundationmodelsandkmeansclustering AT lunamelendezjorgeluis aipowereddetectionandquantificationofpostharvestphysiologicaldeteriorationppdincassavausingyolofoundationmodelsandkmeansclustering AT gimodewinnie aipowereddetectionandquantificationofpostharvestphysiologicaldeteriorationppdincassavausingyolofoundationmodelsandkmeansclustering AT tranthierry aipowereddetectionandquantificationofpostharvestphysiologicaldeteriorationppdincassavausingyolofoundationmodelsandkmeansclustering AT zhangxiaofei aipowereddetectionandquantificationofpostharvestphysiologicaldeteriorationppdincassavausingyolofoundationmodelsandkmeansclustering AT selvarajmichaelgomez aipowereddetectionandquantificationofpostharvestphysiologicaldeteriorationppdincassavausingyolofoundationmodelsandkmeansclustering |