HawkEye: AI-Driven Software for Objective Analysis and Characterization of Nodular Cast Iron Microstructures
Source abstract
Abstract
Metallographic evaluation of nodular cast iron is crucial for quality control in the foundry industry. Traditionally, this process relies on experts who visually interpret microscopic images. This study introduces HawkEye, a comprehensive software solution that automates metallographic analysis using advanced computer vision and deep learning models. Specifically, HawkEye software dynamically adapts its processing workflow based on the input image and its typological classification. The software supports both etched and non-etched specimens and automates the segmentation and classification of graphite nodules, gathering their morphological descriptors; it identifies microstructural phases and provides a global quality assessment. All these functions are embedded into a user-friendly interface designed for both laboratory and industrial use. Nevertheless, the key contribution of this work is the replacement of subjective evaluation with a reproducible, AI-driven approach, which significantly enhances the objectivity, traceability, and scalability of metallurgical analysis. In fact, the proposed approach achieves 99% accuracy in nodule classification compared to manual expert assessment, reduces manual image processing steps, and introduces a novel method for ferrite/perlite measurement in combination with carbide detection using YOLO and SAM models.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Aluminum Alloy Microstructure Properties · Microstructure and Mechanical Properties of Steels · Metallurgy and Material Forming
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Azterlan Member of Basque Research Team Alliance (BRTA), Aliendalde Etxetaldea 6, 48200 Durango, Spain
References (78)
Show source-provided references
1. Li, D., Slater, C., Cai, H., Hou, X., Li, Y., and Wang, Q. (2023). Joining Technologies for Aluminium Castings—A Review. Coatings, 13.10.3390/coatings13050958 ↗
2. Global trends and status in waste foundry sand management research during the years 1971-2020: A systematic analysis10.1007/s11356-021-13251-8 ↗
3. Advances in multi-scale modeling of solidification and casting processes10.1007/s11837-011-0054-x ↗
4. (2019). Microstructure of Cast Irons—Part 1: Graphite Classification by Visual Analysis (Standard No. UNE-EN ISO 945-1:2019). Available online: https://www.une.org.
5. (2020). Microstructure of Cast Irons—Part 2: Determination of Phase Volume Fractions (Standard No. UNE-EN ISO 945-2:2020). Available online: https://www.une.org.
6. (2023). Microstructure of Cast Irons—Part 4: Ausferritic Spheroidal Graphite Cast Iron (Standard No. UNE-EN ISO 945-4:2023). Available online: https://www.une.org.
7. Sarrionandia, X., Nieves, J., Bravo, B., Pastor-López, I., and Bringas, P.G. (2023). An objective metallographic analysis approach based on advanced image processing techniques. J. Manuf. Mater. Process., 7.10.3390/jmmp7010017 ↗
8. NIH Image to ImageJ: 25 years of image analysis10.1038/nmeth.2089 ↗
9. AmGuss (2025, May 20). Gesellschaft zur Förderung Angewandter Informatik. Available online: https://www.gfai.de/.
10. Technologies, A. (2025, May 20). Image Analysis Software. Available online: https://acetechnologiesgroup.com/product/power-xd-165-195/.
11. Gómez, F.J.P. (2018). Application of Artificial Vision Algorithms to Images of Microscopy and Spectroscopy for the Improvement of Cancer Diagnosis. [Ph.D. Thesis, Universitat Politècnica de València].
12. Segmentation of anatomical elements in wood microscopic images using artificial vision techniques
13. Classification of graphite particles in metallographic images of cast irons – Quantitative image analysis versus deep learning10.1016/j.matchar.2024.114333 ↗
14. A tutorial on the segmentation of metallographic images: Taxonomy, new MetalDAM dataset, deep learning-based ensemble model, experimental analysis and challenges10.1016/j.inffus.2021.09.018 ↗
15. Nunes, I.L. (2020). Development of a Programming Code for Image Processing of Nodular Cast Iron. Advances in Human Factors and Systems Interaction, Springer.
16. Automatic quantification of spheroidal graphite nodules using computer vision techniques10.1007/s11227-018-2579-z ↗
17. Divide and conquer10.1093/jla/2.2.417 ↗
18. Divide-and-conquer matrix factorization
19. Divide-and-conquer for parallel processing10.1109/TC.1983.1676280 ↗
20. Improved mosaic: Algorithms for more complex images
21. Affine-invariant recognition of gray-scale characters using global affine transformation correlation10.1109/34.917573 ↗
22. Enhancement of Mine Images Based on HSV Color Space10.1109/ACCESS.2024.3403452 ↗
23. A survey on image data augmentation for deep learning10.1186/s40537-019-0197-0 ↗
24. A survey of image classification methods and techniques for improving classification performance10.1080/01431160600746456 ↗
25. Qian, S., Ning, C., and Hu, Y. (2021, January 26–28). MobileNetV3 for image classification. Proceedings of the 2021 IEEE 2nd International Conference on Big Data, Artificial Intelligence and Internet of Things Engineering (ICBAIE), Nanchang, China.10.1109/ICBAIE52039.2021.9389905 ↗
26. Alam, F., Ofli, F., Imran, M., Alam, T., and Qazi, U. (2020, January 3–6). Deep learning benchmarks and datasets for social media image classification for disaster response. Proceedings of the 2020 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), Hague, The Netherlands.10.1109/ASONAM49781.2020.9381294 ↗
27. A deep multi-modal CNN for multi-instance multi-label image classification10.1109/TIP.2018.2864920 ↗
28. Hyperspectral image classification using CNN: Application to industrial food packaging10.1016/j.foodcont.2021.107962 ↗
29. Determining the freshness of fruits in the food industry by image classification using transfer learning10.1007/s11042-022-12150-5 ↗
30. Using convolution neural network for defective image classification of industrial components
31. Askeland, D.R., and Wright, W.J. (2010). The Science and Engineering of Materials, Cengage Learning.
32. German, R.M. (1998). Sintering Theory and Practice, John Wiley & Sons.
33. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
34. Banerjee, C., Mukherjee, T., and Pasiliao, E. (2019, January 18–20). An empirical study on generalizations of the ReLU activation function. Proceedings of the 2019 ACM Southeast Conference, Kennesaw, GA, USA.10.1145/3299815.3314450 ↗
35. Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv.
36. Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT Press.
37. Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K.Q. (2017, January 21–26). Densely connected convolutional networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.243 ↗
38. Rajpurkar, P., Irvin, J., Zhu, K., Yang, B., Mehta, H., Duan, T., Ding, D., Bagul, A., Langlotz, C., and Shpanskaya, K. (2017). CheXNet: Radiologist-level pneumonia detection on chest X-rays with deep learning. arXiv.
39. Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (2016, January 27–30). Rethinking the inception architecture for computer vision. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.308 ↗
40. Multi-source transfer learning with convolutional neural networks for lung pattern analysis10.1109/JBHI.2016.2636929 ↗
41. Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L.C. (2018, January 18–22). MobileNetV2: Inverted Residuals and Linear Bottlenecks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00474 ↗
42. Howard, A., Sandler, M., Chu, G., Chen, L.C., Chen, B., Tan, M., Wang, W., Zhu, Y., Pang, R., and Vasudevan, V. (November, January 27). Searching for MobileNetV3. Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, Republic of Korea.
43. Deep learning for classification of ductile iron microstructures based on scanning electron microscopy images
44. Guo, C., Pleiss, G., Sun, Y., and Weinberger, K.Q. (2017, January 6–11). On calibration of modern neural networks. Proceedings of the 34th International Conference on Machine Learning (ICML), Sydney, Australia.
45. Hendrycks, D., and Gimpel, K. (2016). A baseline for detecting misclassified and out-of-distribution examples in neural networks. arXiv.
46. Vander Voort, G. (2004). Metallography, Principles and Practice, ASM International.10.31399/asm.hb.v09.a0003752 ↗
47. Buehler, B. (2013). Guide to Materials Characterization and Chemical Analysis, John Wiley & Sons.
48. A survey of convolutional neural networks: Analysis, applications, and prospects10.1109/TNNLS.2021.3084827 ↗
49. Krizhevsky, A., Sutskever, I., and Hinton, G.E. (2012, January 3–6). ImageNet classification with deep convolutional neural networks. Proceedings of the Advances in Neural Information Processing Systems, Lake Tahoe, NV, USA.
50. Graphite Particle Segmentation Method for Spheroidal Graphite Cast Iron Based on Improved DeepLabv3+
51. A new approach to calculate the nodule density of ductile cast iron graphite using a Level Set10.1016/j.measurement.2016.04.029 ↗
52. Microstructure analysis of spheroidal graphite iron (SGI) using hybrid image processing approach
53. Classification of ductile cast iron specimens: A machine learning approach10.3221/IGF-ESIS.42.25 ↗
54. From Individual Graphite Assignment to an Improved Digital Image Analysis of Ductile Iron
55. (2024). Standard Test Method for Evaluating the Microstructure of Graphite in Iron Castings (Standard No. ASTM A247).
56. (2017). Compacted (Vermicular) Graphite Cast Irons—Classification (Standard No. UNE-EN ISO 16112:2017). Available online: https://www.une.org.
57. He, K., Gkioxari, G., Dollár, P., and Girshick, R. (2017, January 22–29). Mask R-CNN. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy.10.1109/ICCV.2017.322 ↗
58. A computer vision approach for automated analysis and classification of microstructural image data10.1016/j.commatsci.2015.08.011 ↗
59. CARACTERIZACIÓN DE NÓDULOS DE GRAFITO USANDO LA TÉCNICA DE MORFOLOGÍA MATEMÁTICA GRAPHITE NODULES CHARACTERIZATION USING MATHEMATICAL MORPHOLOGY TECHNIQUES
60. Nieves, J., Cabello, A., and Bravo, B. (2024). Classifying and Characterizing Fast Nodular Iron Casting Metallographies by Applying a Similarity Search Method. Sci, 6.10.3390/sci6040077 ↗
61. Callister, W.D., and Rethwisch, D.G. (2020). Materials Science and Engineering: An Introduction, Wiley.
62. Davis, J.R. (1996). ASM Specialty Handbook: Cast Irons, ASM International.
63. Struers (2024, March 01). Metallographic Preparation of Cast Iron. Technical Application Note. Available online: https://www.struers.com/en/Knowledge/Materials/Cast-Iron#.
64. Automatic microstructure recognition and classification based on deep learning
65. Deep learning-based classification of microstructure in steel
66. Iron carbide: An ancient advanced material10.1002/smll.201000437 ↗
67. A high-precision automatic recognition method based on target detection for nanometer scaled precipitates or carbides in different alloys10.1016/j.jmrt.2023.09.123 ↗
68. A comprehensive review of yolo architectures in computer vision: From yolov1 to yolov8 and yolo-nas10.3390/make5040083 ↗
69. Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A.C., and Lo, W.Y. (2023, January 2–6). Segment anything. Proceedings of the IEEE/CVF International Conference on Computer Vision, Paris, France.10.1109/ICCV51070.2023.00371 ↗
70. Pai, K.K., Agarwal, M., Sinha, A., Jasmine, M., and N, J.C.K. (2024, January 15–17). Aerial Image Segmentation Using YOLO v8 and SAM Pipeline. Proceedings of the 2024 IEEE Silchar Subsection Conference (SILCON 2024), Agartala, India.10.1109/SILCON63976.2024.10910484 ↗
71. Kim, K., Kim, K., and Jeong, S. (2023). Application of YOLO v5 and v8 for Recognition of Safety Risk Factors at Construction Sites. Sustainability, 15.10.3390/su152015179 ↗
72. Microstructural and chemical surface and rim zone changes of ferrite-perlite 42CrMo4 steel after electrochemical machining10.1002/mawe.202100087 ↗
73. A survey on artificial intelligence trends in smart manufacturing
74. Wolf, T., Debut, L., Sanh, V., Chaumond, J., Delangue, C., Moi, A., Cistac, P., Rault, T., Louf, R., and Funtowicz, M. (2019). HuggingFace’s Transformers: State-of-the-art Natural Language Processing. arXiv.10.18653/v1/2020.emnlp-demos.6 ↗
75. Amershi, S., Weld, D., Vorvoreanu, M., Fourney, A., Nushi, B., Collisson, P., Suh, J., Cakmak, M., Kamar, E., and Horvitz, E. (2019, January 4–9). Guidelines for Human-AI Interaction. Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems, Glasgow, UK.10.1145/3290605.3300233 ↗
76. Splitting ore from X-ray image based on improved robust concave-point algorithm10.7717/peerj-cs.1263 ↗
77. Vehicle-logo recognition based on modified HU invariant moments and SVM10.1007/s11042-017-5254-0 ↗
78. Microscopic Image Dataset with Segmentation and Detection Labels for Microplastic Analysis in Sewage: Enhancing Research and Environmental Monitoring10.3390/microplastics3020016 ↗