SavedAdd your journal

Journals / Journal of Agricultural Sciences / 2026 / Volume: 32 Issue: 3

Nondestructive Detection of Hazelnut Defects Using X-ray Imaging and Deep Learning-Based Segmentation

Sultan Murat Yılmaz(Giresun Üniversitsi)0000-0001-6819-6669
Serap Çakar Kaman(Sakarya University)0000-0002-3682-0831
Erkan Güler(Giresun University)0000-0001-7225-0859
Pages
—
Publication Date
2026-07-28
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

Consequently, with joint usage of defect detection and segmentation, the developed method provides a more objective, accurate, and reliable process for assessing hazelnut quality.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:The hazelnut (Corylus avellana L.) is a strategic agricultural product of high economic and nutritional value.
📊
Key Findings & Data:The most common method for determining quality in the literature and industry is calculating the percentage of hazelnut kernels based on the ratio of sound kernels.
💡
Conclusion & Impact:Consequently, with joint usage of defect detection and segmentation, the developed method provides a more objective, accurate, and reliable process for assessing hazelnut quality.
🔬Design:Research Article
📍Scope:Comprehensive Sample
⚙️Variables:Hazelnut · Deep Learning · Defect Detection

Abstract

The hazelnut (Corylus avellana L.) is a strategic agricultural product of high economic and nutritional value. Turkiye is the world leader in hazelnut production and export. The quality of hazelnuts is critically essential for international competitiveness and economic returns. The most common method for determining quality in the literature and industry is calculating the percentage of hazelnut kernels based on the ratio of sound kernels. However, this method relies on human observation, which can lead to errors and inconsistencies. In particular, this observation-based method sometimes fails to detect defects in the hazelnut kernel. Recently, nondestructive quality determination methods, particularly X-ray imaging technology, have allowed for the quick and accurate detection of internal and external defects in food products. However, the hazelnut industry has only recently started to adopt these technologies and deep learning–based computer vision methods. Significant advantages in terms of accuracy and efficiency for analyzing the quality of hazelnuts, recognizing objects, and detecting defects are offered by nondestructive food processing technologies and artificial intelligence-based approaches. This study created and made publicly available a unique dataset of X-ray images for defect detection in hazelnut kernels. Defect detection was performed using deep learning–based object detection algorithms, including YOLOv5, YOLOv8, Faster R CNN, and SSD, whereas segmentation was achieved using K-means clustering, yielding successful results. Consequently, with joint usage of defect detection and segmentation, the developed method provides a more objective, accurate, and reliable process for assessing hazelnut quality.

🔖

Cite This Article

Yılmaz, S. M., Kaman, S. Ç., Güler, E. (2026). Nondestructive Detection of Hazelnut Defects Using X-ray Imaging and Deep Learning-Based Segmentation. Journal of Agricultural Sciences, Volume: 32 Issue: 3. https://doi.org/10.15832/ankutbd.1719208

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (44)

  1. Abasi S, Minaei S, Jamshidi B & Fathi D (2018). Dedicated nondestructive devices for food quality measurement: A review. Trends in Food Science & Technology 78:197-205. https://doi.org/10.1016/j.tifs.2018.05.009
  2. Arciuolo R, Santos C, Soares C, Castello G, Spigolon N, Chiusa G, Lima N & Battilani P (2020). Molecular Characterization of Diaporthe Species Associated With Hazelnut Defects. Front. Plant Sci. 11: 611655. doi: 10.3389/fpls.2020.611655
  3. Arendse E, Fawole O A, Magwaza L S & Opara U L (2018). Nondestructive prediction of internal and external quality attributes of fruit with thick rind: A review. Journal of Food Engineering 217: 11-23. https://doi.org/10.1016/j.jfoodeng.2017.08.009
  4. Ataş İ (2023). Performance Evaluation of Jaccard-Dice Coefficient on Building Segmentation from High Resolution Satellite Images. Balkan Journal of Electrical and Computer Engineering 11(1): 100-106. https://doi.org/10.17694/bajece.1212563
  5. Ayyildiz E, Yildiz A, Taskin A & Ozkan C (2023). An interval valued Pythagorean fuzzy AHP integrated quality function deployment methodology for hazelnut production https://doi.org/10.1016/j.eswa.2023.120708 in Turkiye. Expert Systems with Applications 231: 100708.
  6. Baki R (2023). The evaluation of target markets for hazelnut exports with the classification approach of potential market alternatives. British Food Journal 125(10):3540-3552. https://doi.org/10.1108/BFJ-02-2023-0100
  7. Bostan S Z & Karakaya O (2024). Morphological, chemical, and molecular characterization of a new late-leafing and high fruit quality hazelnut (Corylus avellana L.) genotype. Genetic Resources and Crop Evolution 71: 5113–5126. https://doi.org/10.1007/s10722-024-01968-7
  8. Bostan S Z (2019). Nut and kernel defects in hazelnut (In Turkish). Akademik Ziraat Dergisi 8(Special Issue): 157-166. https://doi.org/10.29278/azd.644005
  9. de Benedetta F, Giaccone M, Pica F, Lisanti M T, Vinale F, Turrà D, Giacca G M & Bernardo U (2023). Fruit Phenology of Two Hazelnut Cultivars and Incidence of Damage by Halyomorpha halys in Treated and Untreated Hazel Groves. Horticulturae 9(6): 727. https://doi.org/10.3390/horticulturae9060727
  10. Dönmez E, Kılıçarslan S & Diker A (2024). Classification of hazelnut varieties based on bigtransfer deep learning model. European Food Research and Technology 250: 1433-1442. https://doi.org/10.1007/s00217-024-04468-1
  11. El-Mesery H S, Mao H & Abomohra A E-F (2019). Applications of Nondestructive Technologies for Agricultural and Food Products Quality Inspection. Sensors 19(4): 846. https://doi.org/10.3390/s19040846
  12. Erbaş N, Cınarer G & Kilic K (2022). Classification of hazelnuts according to their quality using deep learning algorithms. Czech Journal of Food Sciences 40(3): 240-248. https://doi.org/10.17221/21/2022-CJFS
  13. FAO organization (2023). FAOSTAT Online Statistical Service. Rome: FAO. Available online at: https://www.fao.org/faostat/en/#data/QV
  14. Gencturk B, Arsoy S, Taspinar Y S, Cinar I, Kursun R, Yasin E T & Koklu M (2023). Detection of hazelnut varieties and development of mobile application with CNN data fusion feature reduction-based models. European Food Research and Technolog 250: 97-110. https://doi.org/10.1007/s00217-023-04369-9
  15. Gülsoy E, Şimşek M, & Çevik C (2019). Determination of Fruit Quality Traits in Some Hazelnut Cultivars Grown at Different Altitudes and Locations in Ordu Province (In Turkish). International Journal of Agriculture and Wildlife Science (IJAWS) 5(1): 25-30. https://doi.org/10.24180/ijaws.506932
  16. Herfandi H, Sitanggang O S, Nasution M R A, Nguyen H, Jang Y M (2024). Real-time patient indoor health monitoring and location tracking with optical camera communications on the Internet of Medical Things. Applied Sciences 14(3): 1153. https://doi.org/10.3390/app14031153
  17. İsbakan H & Bostan S Z (2020). Relationships between plant morphological traits, nut yield and quality traits in hazelnut (In Turkish). Ordu University Journal of Science and Technology 10(1): 32-45
  18. Kan E, Akgün M & Turan A (2024). Effect of Brown Marmorated Stink Bug [Halyomorpha halys Stal (Hemiptera:Pentatomidae)] on Physical Traits of Hazelnuts (In Turkish). The Black Sea Journal of Sciences 14(3):1654-1664. https://doi.org/10.31466/kfbd.1462141
  19. Karakaya O, Yaman M, Balta F, Yilmaz M & Balt M F (2023). Assessment of genetic diversity revealed by morphological traits and ISSR markers in hazelnut germplasm (Corylus avellana L.) from Eastern Black Sea Region, Turkiye. Genet Resour Crop Evol 70: 525–537. https://doi.org/10.1007/s10722-022-01444-0 machine learning
  20. Kayakuş M, Kabas O, Ünal İ, Paçacı S & Dinca M N (2024). Nondestructive prediction of hazelnut and hazelnut kernel deformation energy using techniques. https://doi.org/10.1080/10942912.2024.2317749 International Journal of Food Properties 27(1): 326-340.
  21. Khanam R & Hussain M (2024). What is YOLOv5: A deep look into the internal features of the popular object detector. arXiv preprint. https://doi.org/10.48550/arXiv.2407.20892
  22. Khosa I & Pasero E (2014) Feature extraction in X-ray images for hazelnuts classification. 14. International Joint Conference on Neural Networks (IJCNN). Beijing. China. https://doi.org/10.1109/IJCNN.2014.6889661.
  23. Król K, & Gantner M (2020). Morphological Traits and Chemical Composition of Hazelnut from Different Geographical Origins: A Review. Agriculture 10(9): 375. https://doi.org/10.3390/agriculture10090375
  24. Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu C-Y & Berg A C (2016) SSD: Single Shot MultiBox Detector. Computer Vision – ECCV 2016. Lecture Notes in Computer Science. 9905. Springer, Cham. https://doi.org/10.1007/978-3-319-46448-0_2
  25. Ma M, Fu H, Wang Y, Lu Z, Wang Z, Cheng J, Liu X, Dai H, Pi F & Wang J (2025). Nondestructive classification of internal defects in camellia seeds and chestnuts using X-ray imaging: optimization and comparison of deep learning classifiers. Food Control 176: 111367. https://doi.org/10.1016/j.foodcont.2025.111367
  26. Mahanti N K, Pandiselvam R, Kothakota A, Padma I S, Chakraborty S K, Kumar M & Cozzolino D (2022). Emerging nondestructive imaging techniques for fruit damage detection: Image processing and analysis. Trends in Food Science & Technology 120: 418-438. https://doi.org/10.1016/j.tifs.2021.12.021 defects
  27. Maier G, Shevchyk A, Flitter M, Gruna R, Längle T, Hanebeck U D & Beyerer J (2021). Motion-based visual inspection of optically indiscernible on the example of hazelnuts. Computers and Electronics in Agriculture 185: 106147. https://doi.org/10.1016/j.compag.2021.106147
  28. Manavalan R (2020). Automatic identification of diseases in grains crops through computational approaches: A review. Computers and Electronics in Agriculture 178: 105802. https://doi.org/10.1016/j.compag.2020.105802
  29. Ozdemir I O, Tuncer C, Solmaz F G & Ozturk B (2023). The Impact of Green Shield Bug (Palomena prasina [Hemiptera: Pentatomidae]) Infestation on Antioxidant Enzyme Activities in Hazelnut (Corylus avellana L. cvs. ‘Tombul,’ ‘Palaz’ and ‘Çakıldak’). Erwerbs-Obstbau 65: 767–773. https://doi.org/10.1007/s10341-022-00713-7 oxidation assessment
  30. Pannico A, Schouten R E, Basile B, Romano R, Woltering E J & Cirillo C (2015). Nondestructive detection of flawed hazelnut kernels and lipid using https://doi.org/10.1016/j.jfoodeng.2015.03.015 NIR spectroscopy. Journal of Food Engineering 16: 42-48.
  31. Pham V, Pham C & Dang T (2020). Road Damage Detection and Classification with Detectron2 and Faster R-CNN. 2020 IEEE International Conference on Big Data (Big Data). Atlanta. USA. https://doi.org/10.1109/BigData50022.2020.9378027.
  32. Romero-Aroca A, Rovira M, Cristofori V, & Silvestri C (2021). Hazelnut Kernel Size and Industrial Aptitude. Agriculture 11(11): 1115. https://doi.org/10.3390/agriculture11111115
  33. Ropodi A I, Panagou E Z & Nychas G -J E (2016). Data mining derived from food analyses using non-invasive/nondestructive analytical techniques; determination of food authenticity, quality & safety in tandem with computer science disciplines. Trends in Food Science & Technology 50: 11-25. https://doi.org/10.1016/j.tifs.2016.01.011
  34. Saruhan İ & Şen M (2016). Determining the spotted kernel damage of true bugs (Hemiptera: Pentatomidae, Coreidae and Acanthosomatidae) on different hazelnut (Corylus avellana L.) cultivars (In Turkish). Anadolu Journal of Agricultural Sciences 31(3): 337-344. https://doi.org/10.7161/omuanajas.269986
  35. Shakiba N, Gerdes A, Holz N, Wenck S, Bachmann R, Schneider T, Seifert S, Fischer M & Hackl T (2022). Determination of the geographical origin of hazelnuts (Corylus avellana L.) by Near-Infrared spectroscopy (NIR) and a Low-Level Fusion with nuclear magnetic resonance (NMR). Microchemical Journal 174: 107066. https://doi.org/10.1016/j.microc.2021.107066
  36. Taner A, Öztekin Y B & Duran H (2021). Performance Analysis of Deep Learning CNN Models for Variety Classification in Hazelnut. Sustainability 13(12): 6527. https://doi.org/10.3390/su13126527
  37. Terven J, Córdova-Esparza D -M & Romero-González J -A (2023). A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS. Machine Learning and Knowledge Extraction 5(4): 1680-1716. https://doi.org/10.3390/make5040083
  38. Turan A (2023). Determination of Some Traits on Arrival of Hazelnut at Purchasing Points: The Case of Giresun (In Turkish). Akademik Ziraat Dergisi 12(special issue): 99-108. https://doi.org/10.29278/azd.1355568
  39. Ünal Z & Aktaş H (2023). Classification of hazelnut kernels with deep learning. Postharvest Biology and Technology 197: 112225. https://doi.org/10.1016/j.postharvbio.2022.112225
  40. Valeriano T, Fischer K, Ginaldi F, Giustarini L, Castello G & Bregaglio S (2022). Rotten Hazelnuts Prediction via Simulation Modeling—A Case Study on the Turkish Hazelnut Sector. Front. Plant Sci. 13: 766493. https://doi.org/10.3389/fpls.2022.766493 Wang J, Lin Y, Li Q, Lu Z, Qian J, Dai H, Pi F, Liu X & He Y (2024). Nondestructive detection and grading of chilling injury-induced lignification of kiwifruit using X-ray computer tomography and machine learning. Computers and Electronics in Agriculture 218: 108658. https://doi.org/10.1016/j.compag.2024.108658
  41. Xue Q, Miao P, Miao K, Yu Y & Li Z (2022). X-ray-based machine vision technique for detection of internal defects of sterculia seeds. Journal of Food Science 87: 3386–3395. https://doi.org/10.1111/1750-3841.16237
  42. Yılmaz S M, ÇAKAR KAMAN S & Güler E (2025). Hazelnut Kernel Percentage Calculation System with DCIoU and Neighborhood Relationship Algorithm. Processes 13(8): 2414. https://doi.org/10.3390/pr13082414
  43. Zehi B, Afshari A, Noori S M A, Jannat B, & Hashemi M (2020). The Effects of X-ray Irradiation on Safety and Nutritional Value of Food: A Systematic Review Article. Current Pharmaceutical Biotechnology 21(10): 919-926. https://doi.org/10.2174/1389201021666200219093834
  44. Zhu L, Spachos P, Pensini E & Plataniotis K N (2021). Deep learning and machine vision for food processing: A survey. Current Research in Food Science 4: 233-249. https://doi.org/10.1016/j.crfs.2021.03.009