1
|
Hamdy S, Charrier A, Corre LL, Rasti P, Rousseau D. Toward robust and high-throughput detection of seed defects in X-ray images via deep learning. PLANT METHODS 2024; 20:63. [PMID: 38711143 DOI: 10.1186/s13007-024-01195-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/11/2023] [Accepted: 04/26/2024] [Indexed: 05/08/2024]
Abstract
BACKGROUND The detection of internal defects in seeds via non-destructive imaging techniques is a topic of high interest to optimize the quality of seed lots. In this context, X-ray imaging is especially suited. Recent studies have shown the feasibility of defect detection via deep learning models in 3D tomography images. We demonstrate the possibility of performing such deep learning-based analysis on 2D X-ray radiography for a faster yet robust method via the X-Robustifier pipeline proposed in this article. RESULTS 2D X-ray images of both defective and defect-free seeds were acquired. A deep learning model based on state-of-the-art object detection neural networks is proposed. Specific data augmentation techniques are introduced to compensate for the low ratio of defects and increase the robustness to variation of the physical parameters of the X-ray imaging systems. The seed defects were accurately detected (F1-score >90%), surpassing human performance in computation time and error rates. The robustness of these models against the principal distortions commonly found in actual agro-industrial conditions is demonstrated, in particular, the robustness to physical noise, dimensionality reduction and the presence of seed coating. CONCLUSION This work provides a full pipeline to automatically detect common defects in seeds via 2D X-ray imaging. The method is illustrated on sugar beet and faba bean and could be efficiently extended to other species via the proposed generic X-ray data processing approach (X-Robustifier). Beyond a simple proof of feasibility, this constitutes important results toward the effective use in the routine of deep learning-based automatic detection of seed defects.
Collapse
Affiliation(s)
- Sherif Hamdy
- GEVES, Station Nationale d'Essais de Semences, 25 Georges Morel, 49070, Beaucouze, France
| | - Aurélie Charrier
- GEVES, Station Nationale d'Essais de Semences, 25 Georges Morel, 49070, Beaucouze, France
| | - Laurence Le Corre
- GEVES, Station Nationale d'Essais de Semences, 25 Georges Morel, 49070, Beaucouze, France
| | - Pejman Rasti
- Laboratoire Angevin de Recherche en Ingénierie des Systèmes (LARIS), UMR INRAe IRHS, Université d'Angers, 62 Avenue Notre Dame du Lac, 49100, Angers, France
- Centre d'Études et de Recherche pour l'Aide à la Décision (CERADE), École d'ingénieurs (ESAIP), 49100, Angers, France
| | - David Rousseau
- Laboratoire Angevin de Recherche en Ingénierie des Systèmes (LARIS), UMR INRAe IRHS, Université d'Angers, 62 Avenue Notre Dame du Lac, 49100, Angers, France.
- IRHS, INRAE, Institut Agro, Univ. Angers, SFR4207 QuaSaV, 42 Georges Morel CS 60057, 49071, Beaucouze, France.
| |
Collapse
|
2
|
Qin Z, Zhang Z, Hua X, Yang W, Liang X, Zhai R, Huang C. Cereal grain 3D point cloud analysis method for shape extraction and filled/unfilled grain identification based on structured light imaging. Sci Rep 2022; 12:3145. [PMID: 35210561 PMCID: PMC8873360 DOI: 10.1038/s41598-022-07221-4] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/07/2021] [Accepted: 02/07/2022] [Indexed: 11/09/2022] Open
Abstract
Cereals are the main food for mankind. The grain shape extraction and filled/unfilled grain recognition are meaningful for crop breeding and genetic analysis. The conventional measuring method is mainly manual, which is inefficient, labor-intensive and subjective. Therefore, a novel method was proposed to extract the phenotypic traits of cereal grains based on point clouds. First, a structured light scanner was used to obtain the grains point cloud data. Then, the single grain segmentation was accomplished by image preprocessing, plane fitting, region growth clustering. The length, width, thickness, surface area and volume was calculated by the specified analysis algorithms for grain point cloud. To demonstrate this method, experimental materials included rice, wheat and corn were tested. Compared with manual measurement results, the average measurement error of grain length, width and thickness was 2.07%, 0.97%, 1.13%, and the average measurement efficiency was about 9.6 s per grain. In addition, the grain identification model was conducted with 25 grain phenotypic traits, using 6 machine learning methods. The results showed that the best accuracy for filled/unfilled grain classification was 90.184%.The best accuracy for indica and japonica identification was 99.950%, while for different varieties identification was only 47.252%. Therefore, this method was proved to be an efficient and effective way for crop research.
Collapse
Affiliation(s)
- Zhijie Qin
- College of Engineering, Huazhong Agricultural University, Wuhan, 430070, People's Republic of China
| | - Zhongfu Zhang
- College of Engineering, Huazhong Agricultural University, Wuhan, 430070, People's Republic of China
| | - Xiangdong Hua
- College of Engineering, Huazhong Agricultural University, Wuhan, 430070, People's Republic of China
| | - Wanneng Yang
- National Key Laboratory of Crop Genetic Improvement, National Center of Plant Gene Research (Wuhan), Huazhong Agricultural University, Wuhan, 430070, People's Republic of China
| | - Xiuying Liang
- College of Engineering, Huazhong Agricultural University, Wuhan, 430070, People's Republic of China
| | - Ruifang Zhai
- College of Informatics, Huazhong Agricultural University, Wuhan, 430070, People's Republic of China
| | - Chenglong Huang
- College of Engineering, Huazhong Agricultural University, Wuhan, 430070, People's Republic of China.
| |
Collapse
|
3
|
Danilevicz MF, Bayer PE, Nestor BJ, Bennamoun M, Edwards D. Resources for image-based high-throughput phenotyping in crops and data sharing challenges. PLANT PHYSIOLOGY 2021; 187:699-715. [PMID: 34608963 PMCID: PMC8561249 DOI: 10.1093/plphys/kiab301] [Citation(s) in RCA: 14] [Impact Index Per Article: 4.7] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/04/2020] [Accepted: 05/26/2021] [Indexed: 05/06/2023]
Abstract
High-throughput phenotyping (HTP) platforms are capable of monitoring the phenotypic variation of plants through multiple types of sensors, such as red green and blue (RGB) cameras, hyperspectral sensors, and computed tomography, which can be associated with environmental and genotypic data. Because of the wide range of information provided, HTP datasets represent a valuable asset to characterize crop phenotypes. As HTP becomes widely employed with more tools and data being released, it is important that researchers are aware of these resources and how they can be applied to accelerate crop improvement. Researchers may exploit these datasets either for phenotype comparison or employ them as a benchmark to assess tool performance and to support the development of tools that are better at generalizing between different crops and environments. In this review, we describe the use of image-based HTP for yield prediction, root phenotyping, development of climate-resilient crops, detecting pathogen and pest infestation, and quantitative trait measurement. We emphasize the need for researchers to share phenotypic data, and offer a comprehensive list of available datasets to assist crop breeders and tool developers to leverage these resources in order to accelerate crop breeding.
Collapse
Affiliation(s)
- Monica F. Danilevicz
- School of Biological Sciences and Institute of Agriculture, University of Western Australia, Perth, Western Australia 6009, Australia
| | - Philipp E. Bayer
- School of Biological Sciences and Institute of Agriculture, University of Western Australia, Perth, Western Australia 6009, Australia
| | - Benjamin J. Nestor
- School of Biological Sciences and Institute of Agriculture, University of Western Australia, Perth, Western Australia 6009, Australia
| | - Mohammed Bennamoun
- Department of Computer Science and Software Engineering, University of Western Australia, Perth, Western Australia 6009, Australia
| | - David Edwards
- School of Biological Sciences and Institute of Agriculture, University of Western Australia, Perth, Western Australia 6009, Australia
- Author for communication:
| |
Collapse
|
4
|
Boukail S, Macharia M, Miculan M, Masoni A, Calamai A, Palchetti E, Dell'Acqua M. Genome wide association study of agronomic and seed traits in a world collection of proso millet (Panicum miliaceum L.). BMC PLANT BIOLOGY 2021; 21:330. [PMID: 34243721 PMCID: PMC8268170 DOI: 10.1186/s12870-021-03111-5] [Citation(s) in RCA: 11] [Impact Index Per Article: 3.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/23/2021] [Accepted: 06/23/2021] [Indexed: 05/28/2023]
Abstract
BACKGROUND The climate crisis threatens sustainability of crop production worldwide. Crop diversification may enhance food security while reducing the negative impacts of climate change. Proso millet (Panicum milaceum L.) is a minor cereal crop which holds potential for diversification and adaptation to different environmental conditions. In this study, we assembled a world collection of proso millet consisting of 88 varieties and landraces to investigate its genomic and phenotypic diversity for seed traits, and to identify marker-trait associations (MTA). RESULTS Sequencing of restriction-site associated DNA fragments yielded 494 million reads and 2,412 high quality single nucleotide polymorphisms (SNPs). SNPs were used to study the diversity in the collection and perform a genome wide association study (GWAS). A genotypic diversity analysis separated accessions originating in Western Europe, Eastern Asia and Americas from accessions sampled in Southern Asia, Western Asia, and Africa. A Bayesian structure analysis reported four cryptic genetic groups, showing that landraces accessions had a significant level of admixture and that most of the improved proso millet materials clustered separately from landraces. The collection was highly diverse for seed traits, with color varying from white to dark brown and width spanning from 1.8 to 2.6 mm. A GWAS study for seed morphology traits identified 10 MTAs. In addition, we identified three MTAs for agronomic traits that were previously measured on the collection. CONCLUSION Using genomics and automated seed phenotyping, we elucidated phylogenetic relationships and seed diversity in a global millet collection. Overall, we identified 13 MTAs for key agronomic and seed traits indicating the presence of alleles with potential for application in proso breeding programs.
Collapse
Affiliation(s)
- Sameh Boukail
- Institute of Life Sciences, Scuola Superiore Sant'Anna, Pisa, Italy
| | - Mercy Macharia
- Institute of Life Sciences, Scuola Superiore Sant'Anna, Pisa, Italy
| | - Mara Miculan
- Institute of Life Sciences, Scuola Superiore Sant'Anna, Pisa, Italy
| | - Alberto Masoni
- School of Agriculture, University of Florence, Florence, Italy
| | | | | | - Matteo Dell'Acqua
- Institute of Life Sciences, Scuola Superiore Sant'Anna, Pisa, Italy.
| |
Collapse
|