Academic Journal
Προβολή σε EDS
Συνδεδεμένο Πλήρες Κείμενο

Optimized wheat seed classification using YOLO with morphological image feature enhancement.

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: Optimized wheat seed classification using YOLO with morphological image feature enhancement.
Συγγραφείς: Deepika B; Department of Computer Science and Engineering, Dhanalakshmi Srinivasan University, Samayapuram, Tiruchirappalli, 621 112, Tamil Nadu, India., Shanmugapriya N; Department of Artificial Intelligence & Data Science, School of Engineering and Technology, Dhanalakshmi Srinivasan University, Samayapuram, Tiruchirappalli, 621 112, Tamil Nadu, India. shanmugapriyan.set@dsuniversity.ac.in., Gopi R; Department of Computer Science and Engineering, Dhanalakshmi Srinivasan Engineering College, Perambalur, 621 212, Tamil Nadu, India.
Πηγή: Scientific reports [Sci Rep] 2026 Feb 28; Vol. 16 (1). Date of Electronic Publication: 2026 Feb 28.
Τύπος έκδοσης: Journal Article
Γλώσσα: English
Στοιχεία περιοδικού: Publisher: Nature Publishing Group Country of Publication: England NLM ID: 101563288 Publication Model: Electronic Cited Medium: Internet ISSN: 2045-2322 (Electronic) Linking ISSN: 20452322 NLM ISO Abbreviation: Sci Rep Subsets: MEDLINE
Imprint Name(s): Original Publication: London : Nature Publishing Group, copyright 2011-
Ιατρικοί όροι (MeSH): Triticum*/classification , Triticum*/anatomy & histology , Seeds*/classification , Seeds*/anatomy & histology , Image Processing, Computer-Assisted*/methods, Detection Algorithms ; Algorithms ; Deep Learning
Περίληψη: The article presents a superior computer vision system to detect and grade wheat seeds. It is concerned about the integration of deep-learning detection and conventional image processing methods to enhance the overall classification accuracy. The current methods of seed classification in wheat seeds have been found to lack proper visibility of the features particularly in low contrast images, small defects, or overlapping of seeds, and also, irregular lighting situations. The conventional feature extractors are weak, and the deep models by itself fail in cases where the morphological features like grooves, cracks, and shriveling are not well pronounced. To overcome these constraints, the proposed YOLO-Integrated Morphological Feature Enhancement Pipeline (Y-MFEP) uses dilation, erosion, opening, closing and top-hat transformations to enhance structural features and detect them using YOLO. The fused images are the improved feature maps and the original images, which allows the YOLO to identify finer seed variations more accurately. Such a hybrid pipeline enhances the visibility of the edges, defects, and texture uniformity without sacrificing the real-time detection performance. The given method is used to grade the quality of wheat at agricultural processing and procurement centers automatically. It guarantees quick, stable, and high-scaling classification of fit, broken, shriveled, and infected seeds. The results demonstrate that Y-MFEP has a major advantage of improving the accuracy, mAP and defect-detection sensitivity, which creates a more dependable and automated wheat quality measurement. The classification accuracy (85–95%), defect sensitivity index (0.775), edge clarity score (78–85), intersection over union (75–82%), and small object detection rate (75–90%) is reached in the proposed method.
Competing Interests: Declarations. Competing interests: The authors declare no competing interests.
References: Madhavan, J., Salim, M., Durairaj, U. & Kotteeswaran, R. Wheat seed classification using neural network pattern recognizer. Mater. Today Proc. 81, 341–345. https://doi.org/10.1016/j.matpr.2021.03.226 (2023). (PMID: 10.1016/j.matpr.2021.03.226)
Lingwal, S., Bhatia, K. K. & Tomer, M. S. Image-based wheat grain classification using convolutional neural network. Multimedia Tools Appl. 80, 35441–35465. https://doi.org/10.1007/s11042-020-10174-3 (2021). (PMID: 10.1007/s11042-020-10174-3)
El-Kenawy, E. S. M. et al. Metaheuristic optimization for improving weed detection in wheat images captured by drones. Mathematics 10(23), 4421. https://doi.org/10.3390/math10234421 (2022). (PMID: 10.3390/math10234421)
Khalid, A., Hameed, A. & Tahir, M. F. Wheat quality: A review on chemical composition, nutritional attributes, grain anatomy, types, classification, and function of seed storage proteins in bread making quality. Front. Nutr. 10, 1053196. https://doi.org/10.3389/fnut.2023.1053196 (2023). (PMID: 10.3389/fnut.2023.1053196369089039998918)
Al Bataineh, A., Kaur, D. & Jalali, S. M. J. Multi-layer perceptron training optimization using nature inspired computing. IEEE Access 10, 36963–36977. https://doi.org/10.1109/ACCESS.2022.3164669 (2022). (PMID: 10.1109/ACCESS.2022.3164669)
Rabieyan, E. et al. Morpho-colorimetric seed traits for the discrimination, classification and prediction of yield in wheat genotypes. Crop Pasture Sci. 74 (4), 294–311. https://doi.org/10.1071/CP22127 (2022). (PMID: 10.1071/CP22127)
Passos, D. & Mishra, P. Automated deep learning pipeline based on advanced optimisations for spectral classification modelling. Chemometr. Intell. Lab. Syst. 215, 104354. https://doi.org/10.1016/j.chemolab.2021.104354 (2021). (PMID: 10.1016/j.chemolab.2021.104354)
Ma, C. et al. GC-IMS technique and applications in grain research. J. Sci. Food. Agric. 104 (15), 9093–9101. https://doi.org/10.1002/jsfa.13622 (2024). (PMID: 10.1002/jsfa.1362238817147)
Mushtaq, M. A. et al. Applications of artificial intelligence in wheat breeding. Sustainability 16 (13), 5688. https://doi.org/10.3390/su16135688 (2024). (PMID: 10.3390/su16135688)
Wang, J. et al. UAV and machine learning-based retrieval of wheat SPAD values. Remote Sens. 13 (24), 5166. https://doi.org/10.3390/rs13245166 (2021). (PMID: 10.3390/rs13245166)
Rabieyan, E. et al. Imaging-based screening of wheat seed characteristics. Crop Pasture Sci. 73 (4), 337–355. https://doi.org/10.1071/CP21500 (2022). (PMID: 10.1071/CP21500)
Mehta, S., Kukreja, V. & Gupta, A. Federated CNNs for wheat disease monitoring. In INCET 2023. (2023). https://doi.org/10.1109/INCET57972.2023.10169991.
Adnan, M. et al. Phosphorous supplements for optimizing wheat yield. Sci. Rep. 12, 11997. https://doi.org/10.1038/s41598-022-16035-3 (2022). (PMID: 10.1038/s41598-022-16035-3358358509283399)
Merrick, L. F. et al. Optimizing plant breeding programs. Agronomy 12 (3), 714. https://doi.org/10.3390/agronomy12030714 (2022). (PMID: 10.3390/agronomy12030714)
Feng, Z. H. et al. Hyperspectral monitoring of powdery mildew in wheat. Front. Plant Sci. 13, 828454. https://doi.org/10.3389/fpls.2022.828454 (2022). (PMID: 10.3389/fpls.2022.828454353866778977770)
Khatri, A. et al. Wheat seed classification using ensemble ML. Scientific Programming, 2022, 2626868. (2022). https://doi.org/10.1155/2022/2626868.
Fazel-Niari, Z. et al. Quality assessment of wheat seed components. Appl. Sci. 12 (9), 4133. https://doi.org/10.3390/app12094133 (2022). (PMID: 10.3390/app12094133)
Baryshev, D. D. et al. ML methods for wheat seed classification. Russian Agricultural Sci. 46 (4), 410–417. https://doi.org/10.3103/S1068367420040047 (2020). (PMID: 10.3103/S1068367420040047)
Ronge, R. V. & Sardeshmukh, M. M. Indian wheat seed classification. In ICACCI 2014. (2014). https://doi.org/10.1109/ICACCI.2014.6968483.
Agarwal, D. & Bachan, P. ML for wheat grain classification. Smart Agric. Technol. 3, 100136. https://doi.org/10.1016/j.atech.2022.100136 (2023). (PMID: 10.1016/j.atech.2022.100136)
Yasar, A. CNN-SVM-based deep features for wheat classification. Eur. Food Res. Technol. 250, 1551–1561. https://doi.org/10.1007/s00217-024-04488-x (2024). (PMID: 10.1007/s00217-024-04488-x)
Dogan, M. & Ozkan, I. A. Optimized ELM for wheat type determination. Neural Comput. Appl. 35, 12565–12581. https://doi.org/10.1007/s00521-023-08354-x (2023). (PMID: 10.1007/s00521-023-08354-x)
Khan, M. et al. Ensemble SVM for wheat genotype classification. Sci. Rep. 14, 22728. https://doi.org/10.1038/s41598-024-72056-0 (2024). (PMID: 10.1038/s41598-024-72056-03934993411442772)
Rokhva, S. & Teimourpour, B. EfficientNetB7-CBAM for real-time food classification. Food Human. 4, 100492. https://doi.org/10.1016/j.foohum.2024.100492 (2025). (PMID: 10.1016/j.foohum.2024.100492)
Raeisi, Z. et al. Attention-based multi-task X-ray classification. Multimedia Tools Appl. 84, 49271–49295. https://doi.org/10.1007/s10006-025-01463-y (2025). (PMID: 10.1007/s10006-025-01463-y)
Bagherpour, H. & Peyruo, N. F. YOLO-based detection of wheat impurities. Sci. Rep. 15, 40436. https://doi.org/10.1038/s41598-025-23032-9 (2025). (PMID: 10.1038/s41598-025-23032-94125389712627783)
Yasar, A. & Golcuk, A. Fusion-based feature extraction for wheat classification. Eur. Food Res. Technol. https://doi.org/10.1007/s00217-025-04720-2 (2025). (PMID: 10.1007/s00217-025-04720-2)
Li, G. et al. Terahertz image enhancement and yolo-based classification model for early germination wheat sprouting detection SSRN. https://doi.org/10.2139/ssrn.5045897 (2025).
Chen, S. et al. Soft X-ray YOLOv8 for maize seed cracks. Comput. Electron. Agric. 216, 108475. https://doi.org/10.1016/j.compag.2023.108475 (2024). (PMID: 10.1016/j.compag.2023.108475)
Pawłowski, J. et al. YOLO CNN for seed size detection. Appl. Sci. 14 (14), 6294. https://doi.org/10.3390/app14146294 (2024). (PMID: 10.3390/app14146294)
Kumar, T. et al. CNN-based wheat cultivar identification. Genet. Resour. Crop Evol. 72, 1633–1648. https://doi.org/10.1007/s10722-024-02042-y (2025). (PMID: 10.1007/s10722-024-02042-y)
Li, G. et al. Deep learning terahertz wheat germination detection. Plant. Methods. 21, 75. https://doi.org/10.1186/s13007-025-01393-6 (2025). (PMID: 10.1186/s13007-025-01393-64044820812125745)
Li, R. & Wu, Y. Improved YOLOv5 wheat ear detection. Electronics 11(11), 1673. https://doi.org/10.3390/electronics11111673 (2022). (PMID: 10.3390/electronics11111673)
Wu, H. et al. FEWheat-YOLO lightweight spike detection. Plants 14 (19), 3058. https://doi.org/10.3390/plants14193058 (2025). (PMID: 10.3390/plants141930584109519912526082)
Sun, J. et al. Rice grain counting via detection. Comput. Electron. Agric. 227, 109490. https://doi.org/10.1016/j.compag.2024.109490 (2024). (PMID: 10.1016/j.compag.2024.109490)
Mavaddati, S. & Razavi, M. Optimized YOLO-ViT for rice classification. (2025). https://doi.org/10.5829/ije.2025.38.10a.19.
Rana, S. et al. Spectral overlap in agriculture via soft classification. MethodsX 11, 103114. https://doi.org/10.1016/j.mex.2024.103114 (2024). (PMID: 10.1016/j.mex.2024.103114)
Kaggle. (n.d.). Wheat variety classification dataset. Retrieved from https://www.kaggle.com/datasets/sudhanshu2198/wheat-variety-classification.
Contributed Indexing: Keywords: Feature fusion; Image processing; Morphological enhancement; Seed quality assessment; Wheat classification; YOLO
Entry Date(s): Date Created: 20260301 Date Completed: 20260627 Latest Revision: 20260627
Update Code: 20260627
PubMed Central ID: PMC13057161
DOI: 10.1038/s41598-026-41846-z
PMID: 41764335
Βάση Δεδομένων: MEDLINE
Περιγραφή
ISSN:2045-2322
DOI:10.1038/s41598-026-41846-z