{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T00:47:37Z","timestamp":1785804457654,"version":"3.56.0"},"reference-count":36,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2025,3,23]],"date-time":"2025-03-23T00:00:00Z","timestamp":1742688000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Symmetry"],"abstract":"<jats:p>The excellent \u201cmirror\u201d effect of medium and high-strength aluminum alloy profiles from the 6-series, achieved through anodizing, is highly valued by customers. Metallographic analysis is a key method for predicting the anodizing effect. However, traditional metallographic analysis methods suffer from unstable accuracy and low efficiency. To address these issues, this paper successfully develops a metallographic grading system by constructing a dataset and integrating computer vision with machine-learning techniques. Based on grain classification, the system automatically determines the metallographic grade by analyzing the proportion of good grain areas. After applying SMOTE sampling and 10-fold cross-validation to the machine-learning algorithm, we conducted a comparative analysis of the model\u2019s performance from the perspectives of accuracy, good grain recall rate, bad grain recall rate, and AUC. The XGBoost model, selected as the final predictive model from 18 machine-learning models due to its superior performance, achieved a grain classification accuracy of 96.21% and a good grain recall rate of 98.07%. Both the accuracy and good grain recall standard deviations were less than 0.02. These results indicate that the model can effectively distinguish between good and bad grains with high robustness. Additionally, the average time for metallographic grading is less than 9 s. In comparison to the instability of traditional manual grading, this method significantly enhances both the accuracy and efficiency of metallographic analysis while also reducing grading costs.<\/jats:p>","DOI":"10.3390\/sym17040482","type":"journal-article","created":{"date-parts":[[2025,3,24]],"date-time":"2025-03-24T13:48:20Z","timestamp":1742824100000},"page":"482","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Machine-Learning-Based Automatic Metallographic Grading System for High-Gloss Anodized Aluminum Profiles"],"prefix":"10.3390","volume":"17","author":[{"given":"Xuda","family":"Xu","sequence":"first","affiliation":[{"name":"School of Material Science and Engineering, Central South University, Changsha 410083, China"},{"name":"Guangdong Hoshion Aluminium Co., Ltd., Zhongshan 528463, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Material Science and Engineering, Central South University, Changsha 410083, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lurong","family":"Li","sequence":"additional","affiliation":[{"name":"Guangdong Hoshion Aluminium Co., Ltd., Zhongshan 528463, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3935-5808","authenticated-orcid":false,"given":"Hongfeng","family":"Huang","sequence":"additional","affiliation":[{"name":"College of Materials Science and Engineering, Guilin University of Technology, Guilin 541004, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fei","family":"Yang","sequence":"additional","affiliation":[{"name":"Guangdong Hoshion Aluminium Co., Ltd., Zhongshan 528463, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunli","family":"Jiang","sequence":"additional","affiliation":[{"name":"Guangdong Institute of Special Equipment Inspection and Research Zhongshan Branch, Zhongshan 528400, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,3,23]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1299","DOI":"10.1002\/sia.6036","article-title":"Effect of AlSiFe on the anodizing process of 6063 aluminum","volume":"48","author":"Hu","year":"2016","journal-title":"Surf. Interface Anal. Sia"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Wang, G., Song, D., Zhou, Z., Klu, E.E., Liu, Y., Liang, N., Jiang, J., Sun, J., and Ma, A. (2020). Effect of Ultrafine Grains on the Coating Reaction and Anticorrosion Performance of Anodized Pure Aluminum. Coatings, 10.","DOI":"10.3390\/coatings10030216"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Tamadon, A., Pons, D.J., Sued, K., and Clucas, D. (2017). Development of Metallographic Etchants for the Microstructure Evolution of A6082-T6 BFSW Welds. Metals, 7.","DOI":"10.3390\/met7100423"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"232","DOI":"10.1016\/j.inffus.2021.09.018","article-title":"A tutorial on the segmentation of metallographic images: Taxonomy, new MetalDAM dataset, deep learning-based ensemble model, experimental analysis and challenges","volume":"78","author":"David","year":"2022","journal-title":"Inf. Fusion"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Naik, D.L., Sajid, H.U., and Kiran, R. (2019). Texture-Based Metallurgical Phase Identification in Structural Steels: A Supervised Machine Learning Approach. Metals, 9.","DOI":"10.3390\/met9050546"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"30858","DOI":"10.1109\/ACCESS.2021.3059505","article-title":"Semi-Supervised Learning Framework for Aluminum Alloy Metallographic Image Segmentation","volume":"9","author":"Dali","year":"2021","journal-title":"IEEE Access"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Matan, R., Ofer, B., and Gal, O. (2022). An end-to-end computer vision methodology for quantitative metallography. Sci. Rep., 12.","DOI":"10.1038\/s41598-022-08651-w"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"135743","DOI":"10.1016\/j.matlet.2023.135743","article-title":"Overcoming optical image challenges in automatic grain size measurement using a novel computer vision algorithm applied to hot deformation of Al-Zn-Mg Powder metallurgy alloy","volume":"357","author":"Katika","year":"2024","journal-title":"Mater. Lett."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"113199","DOI":"10.1016\/j.commatsci.2024.113199","article-title":"Metallographic image segmentation using feature pyramid based recurrent residual U-Net","volume":"244","author":"Majumdar","year":"2024","journal-title":"Comput. Mater. Sci."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"114333","DOI":"10.1016\/j.matchar.2024.114333","article-title":"Classification of graphite particles in metallographic images of cast irons\u2014Quantitative image analysis versus deep learning","volume":"217","author":"Germain","year":"2024","journal-title":"Mater. Charact."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1016\/j.eswa.2023.122146","article-title":"Wire melted mark metallographic image recognition and classification based on semantic segmentation","volume":"238","author":"Shi","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"ref_12","first-page":"59","article-title":"Development status and prospect of artificial intelligence recognition in metallographic inspection","volume":"42","author":"Shen","year":"2024","journal-title":"Phys. Exam. Test."},{"key":"ref_13","first-page":"1075","article-title":"A deep learning-based method for grading the grain size of steel metallographic images","volume":"34","author":"Wang","year":"2023","journal-title":"J. Optoelectron.\u00b7Laser"},{"key":"ref_14","unstructured":"Yue, S., Zhiguo, A., Lijuan, B., Xiurui, G., Wenjin, Y., and Lijun, L. (2023). Automatic ferrite grain size rating method based on deep learning. Hebei Metall., 73\u201377."},{"key":"ref_15","unstructured":"Su, C. (2023). Deep Learning-Based Segmentation and Grading of Metallographic Organization of Carburized Gears. [Master\u2019s Thesis, Jiangnan University]."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1023\/B:VLSI.0000028532.53893.82","article-title":"Realization of the Contrast Limited Adaptive Histogram Equalization (CLAHE) for Real-Time Image Enhancement","volume":"38","author":"Reza","year":"2004","journal-title":"J. Vlsi Signal Process."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Justusson, B.I. (1981). Median filtering: Statistical properties. Two-Dimensional Digital Signal Processing II, Springer.","DOI":"10.1007\/BFb0057597"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"771","DOI":"10.1007\/s12524-022-01645-1","article-title":"Landslide Susceptibility Prediction based on Decision Tree and Feature Selection Methods","volume":"51","author":"Nirbhav","year":"2023","journal-title":"J. Indian Soc. Remote Sens."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"2260","DOI":"10.1007\/s12161-022-02286-3","article-title":"Machine Learning for Varietal Binary Classification of Soybean (Glycine max (L.) Merrill) Seeds Based on Shape and Size Attributes","volume":"15","author":"Necati","year":"2022","journal-title":"Food Anal. Meth."},{"key":"ref_20","first-page":"1","article-title":"ECG signal classification via ensemble learning: Addressing intra and inter-patient variations","volume":"16","author":"Mahajan","year":"2024","journal-title":"Int. J. Inf. Technol."},{"key":"ref_21","first-page":"1","article-title":"Research of decision tree classification algorithm in data mining","volume":"5","author":"Dai","year":"2016","journal-title":"Int. J. Database Theory Appl."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random Forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1189","DOI":"10.1214\/aos\/1013203451","article-title":"Greedy Function Approximation: A Gradient Boosting Machine","volume":"29","author":"Friedman","year":"2001","journal-title":"Ann. Stat."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Chen, T., and Guestrin, C. (2016, January 13\u201317). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge, San Francisco, CA, USA.","DOI":"10.1145\/2939672.2939785"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1016\/S0893-6080(05)80023-1","article-title":"Stacked generalization","volume":"5","author":"Wolpert","year":"1992","journal-title":"Neural Netw."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1055\/s-2007-959037","article-title":"Logistische Regression","volume":"132","author":"Bender","year":"2007","journal-title":"Dtsch. Med. Wochenschr."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"14","DOI":"10.4114\/intartif.vol18iss56pp14-30","article-title":"Naive Bayes vs Logistic Regression: Theory, Implementation and Experimental Validation","volume":"18","author":"Bhowmik","year":"2015","journal-title":"Intel. Artif."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"704","DOI":"10.1117\/1.602417","article-title":"Target classification via support vector machines","volume":"39","author":"Karlsen","year":"2000","journal-title":"Opt. Eng."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"218","DOI":"10.21037\/atm.2016.03.37","article-title":"Introduction to machine learning: K-nearest neighbors","volume":"4","author":"Zhongheng","year":"2016","journal-title":"Ann. Transl. Med."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"2627","DOI":"10.1016\/S1352-2310(97)00447-0","article-title":"Artificial neural networks (the multilayer perceptron)\u2014A review of applications in the atmospheric sciences","volume":"14-15","author":"Gardner","year":"1998","journal-title":"Atmos. Environ."},{"key":"ref_31","first-page":"92","article-title":"Research on Imbalanced Data Sets Classification Method","volume":"39","author":"Quanshang","year":"2013","journal-title":"J. Sci. Educ."},{"key":"ref_32","first-page":"147","article-title":"Effects of Several Evaluation Metrics on Imbalanced Data Learning","volume":"38","author":"Lin","year":"2010","journal-title":"J. South China Univ. Technol. (Nat. Sci. Ed.)"},{"key":"ref_33","first-page":"128","article-title":"Optimization boosting classification based on metrics of imbalanced data","volume":"54","author":"Jianhong","year":"2018","journal-title":"Comput. Eng. Appl."},{"key":"ref_34","first-page":"67","article-title":"Research on gradient lifting Algorithm of unbalanced Data Sets","volume":"3","author":"Yang","year":"2024","journal-title":"Microcomputers"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"4903","DOI":"10.1007\/s10994-022-06296-4","article-title":"A theoretical distribution analysis of synthetic minority oversampling technique (SMOTE) for imbalanced learning","volume":"113","author":"Elreedy","year":"2023","journal-title":"Mach. Learn."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"1866","DOI":"10.12677\/AAM.2023.124193","article-title":"Application of cross-validation method in model comparison","volume":"4","author":"Zhang","year":"2023","journal-title":"Adv. Appl. Math."}],"container-title":["Symmetry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-8994\/17\/4\/482\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T16:58:47Z","timestamp":1760029127000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-8994\/17\/4\/482"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,23]]},"references-count":36,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,4]]}},"alternative-id":["sym17040482"],"URL":"https:\/\/doi.org\/10.3390\/sym17040482","relation":{},"ISSN":["2073-8994"],"issn-type":[{"value":"2073-8994","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,23]]}}}