Design Scheme Style Feature Extraction and Machine Learning Classification Algorithm Construction

Wenjie Wang1*
1 Digital Media Major, Beijing City University, Beijing, China
* Corresponding author: Wenjie Wang. Email: wangwenjie081@outlook.com
International Scientific Technical and Economic Research 2026, Vol. 4, No. 3, pp. 1-21
DOI: 10.67541/istaer2623
Received: 24 May 2026; Revised: 26 June 2026; Accepted: 29 June 2026; Published: 9 July 2026
Abstract

The automatic recognition of design scheme style is a key technology of intelligent design assistance system. Existing methods rely on handcrafted features, and the generalization ability of classifiers is insufficient. This paper proposes a style classification method combining multi-modal feature extraction and improved ensemble classification architecture. At the feature level, a three-modal feature space of structural contour (enhanced histogram of oriented gradients), local texture (encoded by the LBP mutation operator) and global topology (graph convolution embedding) is constructed, and the dimension of the fused feature is compressed to 28% of the original space by a joint PCA‑kernelized dimensionality reduction method, while preserving the nonlinear discriminant structure. At the classification level, a weighted extreme learning machine with adaptive margin adjustment is designed, a multi-branch parallel input and a decision-level weighted voting architecture are introduced, and the loss function is reconstructed by adding a style margin maximization regularization term. 5‑fold stratified cross‑validation is conducted on a dataset containing 5200 samples (8 style types). The experimental results show that the macro F1-score of our method is 88.7%, and the accuracy is 91.5%. Compared with the standard extreme learning machine, the accuracy is improved by 5.3 percentage points, and the generalization error is reduced from 5.8% to 1.2%. Even under strong noise at 5 dB, the accuracy reaches 74.6%, which is 13.8 percentage points higher than the baseline model. The proposed method takes into account both accuracy and robustness, and provides a feasible technical path for efficient recognition of design scheme style.

Keywords
Design scheme style classification Multimodal feature extraction Weighted extreme learning machine Graph convolutional network Margin maximization regularization
References
  1. Liu, X., & Zhang, C. (2024). Data Mining and Pattern Recognition of the Integration of Art Design Style and CAD System. Computer-Aided Design and Applications, 21, 116-131. DOI: 10.14733/cadaps.2024.s19.116-131
  2. Xin, T., Kim, S., & Shangshang, Z. (2025). Classification and Analysis of Packaging Design Styles Based on Visual Feature Extraction. IEEE Access, 13, 206639-206653. DOI: 10.1109/access.2025.3634619
  3. Vijendran, M., Deng, J., Chen, S., Ho, E. S., & Shum, H. P. (2024). Artificial intelligence for geometry-based feature extraction, analysis and synthesis in artistic images: a survey. arXiv preprint arXiv:2412.01450. DOI: 10.1007/s10462-024-11051-3
  4. Kumar, D., Pandey, R. C., & Mishra, A. K. (2024). A review of image features extraction techniques and their applications in image forensic. Multimedia Tools and Applications, 83(40), 87801-87902. DOI: 10.1007/s11042-023-17950-x
  5. Rundo, L., & Militello, C. (2024). Image biomarkers and explainable AI: handcrafted features versus deep learned features. European Radiology Experimental, 8(1), 130. DOI: 10.1186/s41747-024-00529-y
  6. He, J., Guo, J., Zhou, L., & Liu, Y. (2025). Hybrid deep learning and fractional Brownian motion approach for probabilistic RUL prediction in industrial equipment. IEEE Transactions on Instrumentation and Measurement. DOI: 10.1109/tim.2025.3606063
  7. Feng, H., Zhong, C., Zhang, Z., Liu, Y., & Ma, Q. (2026). FFAKAN: A Frequency-Aware Filtering Activation-Based Kolmogorov-Arnold Network for Hyperspectral Image Classification. Remote Sensing, 18(7), 981. DOI: 10.3390/rs18070981
  8. Islam, M. R., Lima, A. A., Das, S. C., Mridha, M. F., Prodeep, A. R., & Watanobe, Y. (2022). A comprehensive survey on the process, methods, evaluation, and challenges of feature selection. IEEE Access, 10, 99595-99632. DOI: 10.1109/access.2022.3205618
  9. Xin, T., Kim, S., & Shangshang, Z. (2025). Classification and Analysis of Packaging Design Styles Based on Visual Feature Extraction. IEEE Access, 13, 206639-206653. DOI: 10.1109/access.2025.3634619
  10. Peng, D., Liu, R., Lu, J., & Zhang, S. (2022). Unsupervised multi-modal modeling of fashion styles with visual attributes. Applied Soft Computing, 115, 108214. DOI: 10.1016/j.asoc.2021.108214
  11. Wulandari, M., Chai, R., Basari, B., & Gunawan, D. (2024). Hybrid feature extractor using discrete wavelet transform and histogram of oriented gradient on Convolutional-Neural-Network-Based palm vein recognition. Sensors, 24(2), 341. DOI: 10.3390/s24020341
  12. Bouchene, M. M. (2024). Bayesian optimization of histogram of oriented gradients (HOG) parameters for facial recognition. The Journal of Supercomputing, 80(14), 20118-20149. DOI: 10.1007/s11227-024-06259-7
  13. Bakheet, S. (2017). An SVM framework for malignant melanoma detection based on optimized HOG features. Computation, 5(1), 4. DOI: 10.3390/computation5010004
  14. Xu, X., & Li, B. (2025). Multi scale supervised entropy weighted binary pattern for texture classification. Scientific Reports, 15(1), 26087. DOI: 10.1038/s41598-025-11245-x
  15. Maher, H. (2024). Texture Analysis and Classification using Local Binary Patterns and Statistical Features. Wasit Journal of Computer and Mathematics Science, 3(3), 79-88. DOI: 10.31185/wjcms.279
  16. Elazab, N., Gab Allah, W., & Elmogy, M. (2024). Computer-aided diagnosis system for grading brain tumor using histopathology images based on color and texture features. BMC Medical Imaging, 24(1), 177. DOI: 10.1186/s12880-024-01355-9
  17. Kaur, M. (2023). A comparative analysis of local binary pattern (LBP) variants for image tamper detection. DOI: 10.21203/rs.3.rs-3608580/v1
  18. Al Saidi, I., Rziza, M., & Debayle, J. (2023). Completed homogeneous LBP for remote sensing image classification. International Journal of Remote Sensing, 44(12), 3815-3836. DOI: 10.1080/01431161.2023.2227320
  19. Meeradevi, T., Sasikala, S., Gomathi, S., & Prabakaran, K. (2023). An analytical survey of textile fabric defect and shade variation detection system using image processing. Multimedia Tools and Applications, 82(4), 6167-6196. DOI: 10.1007/s11042-022-13575-8
  20. Lu, J., Zhang, C., Li, J., Zhao, Y., Qiu, W., Li, T., ... & He, J. (2022). Graph convolutional networks-based method for estimating design loads of complex buildings in the preliminary design stage. Applied Energy, 322, 119478. DOI: 10.1016/j.apenergy.2022.119478
  21. Zhou, Y., Huo, H., Hou, Z., Bu, L., Mao, J., Wang, Y., ... & Bu, F. (2023). Co-embedding of edges and nodes with deep graph convolutional neural networks. Scientific Reports, 13(1), 16966. DOI: 10.1038/s41598-023-44224-1
  22. Baranwal, A., Fountoulakis, K., & Jagannath, A. (2022). Effects of graph convolutions in multi-layer networks. arXiv preprint arXiv:2204.09297. DOI: 10.48550/arXiv.2204.09297
  23. Greenacre, M., Groenen, P. J., Hastie, T., d'Enza, A. I., Markos, A., & Tuzhilina, E. (2022). Principal component analysis. Nature Reviews Methods Primers, 2(1), 100. DOI: 10.1038/s43586-023-00209-y
  24. Bharadiya, J. P. (2023). A tutorial on principal component analysis for dimensionality reduction in machine learning. International Journal of Innovative Science and Research Technology, 8(5), 2028-2032. DOI: 10.5281/zenodo.8002436
  25. Ashraf, A., Nawi, N. M., & Aamir, M. (2023). Adaptive feature selection and image classification using manifold learning techniques. IEEE Access, 12, 40279-40289. DOI: 10.1109/access.2023.3322147
  26. Jia, W., Sun, M., Lian, J., & Hou, S. (2022). Feature dimensionality reduction: a review. Complex & Intelligent Systems, 8(3), 2663-2693. DOI: 10.1007/s40747-021-00637-x
  27. Song, W., Zhang, X., Yang, G., Chen, Y., Wang, L., & Xu, H. (2024). A study on dimensionality reduction and parameters for hyperspectral imagery based on manifold learning. Sensors, 24(7), 2089. DOI: 10.3390/s24072089
  28. Jiao, T., Guo, C., Feng, X., Chen, Y., & Song, J. (2024). A comprehensive survey on deep learning multi-modal fusion: Methods, technologies and applications. Computers, Materials & Continua, 80(1). DOI: 10.32604/cmc.2024.053204
  29. Gao, X., Zhang, G., & Xiong, Y. (2022). Multi-scale multi-modal fusion for object detection in autonomous driving based on selective kernel. Measurement, 194, 111001. DOI: 10.1109/TVT.2022.3230265
  30. Kullu, O., & Cinar, E. (2022). A deep-learning-based multi-modal sensor fusion approach for detection of equipment faults. Machines, 10(11), 1105. DOI: 10.3390/machines10111105
  31. Lu, T., Xiong, J., Zhou, J., Wang, Q., Cen, J., Liu, M., ... & Zhang, J. (2024). Bearing fault diagnosis using multichannel broad learning system based on positive–negative weighted voting mechanism. IEEE Transactions on Instrumentation and Measurement, 73, 1-10. DOI: 10.1109/TIM.2024.3373075
  32. Khan, A., Ali, A., Islam, N., Manzoor, S., Zeb, H., Azeem, M., & Ihtesham, S. (2022). Robust Extreme Learning Machine Using New Activation and Loss Functions Based on M‐Estimation for Regression and Classification. Scientific Programming, 2022(1), 6446080. DOI: 10.1155/2022/6446080
  33. Atallah, E. S., Hagag, A., Ali, E. M., & Abassy, T. A. (2025). Using the Quasi-Newton Method to Solve Nonlinear Least Squares Regression Problems. International Journal of Applied Intelligent Computing and Informatics, 1(1), 9-15. DOI: 10.21608/ijaici.2025.340085.1004