A Vehicle Type Recognition (VTR) system faces challenges in achieving accurate classification when distinguishing between vehicle types with intra-class patterns, such as sedan cars, taxis, vans, minivans, trucks, and buses. The main challenge lies in effectively extracting and preserving discriminant features for each vehicle type to prevent misclassification. Therefore, this paper proposes an efficient regularization approach within the Mask Region-based Convolutional Neural Network (Mask_RCNN) optimizer by integrating Weighted Mean League 2 (WMean_L2) with Stochastic Gradient Distance (SGD). We introduce this model as Mask_RCNN+SGD+WMean_L2. WMean_L2 is formulated to ensure consistency in penalty regardless of model size, providing stability across architectures and simplifying hyperparameter tuning. This approach enhances the preservation of discriminant features while achieving consistent and optimal classification performance. We tested our model on the benchmark database known as Beijing Institute of Technology (BIT), evaluating its performance based on precision, recall, F-score, and accuracy. Our results demonstrate significant efficiency improvements compared to previous studies, with precision ranging from 92.31% to 100%, recall from 94.74% to 100%, and F-score from 93.51% to 100% across six vehicle classes, achieving the highest average accuracy of 97.22%.

[1] Awang S., Azmi N., and Ghani N., “Road Enforcement Monitoring System based on Vehicle Type Recognition Using Sparse Filtering Convolutional Neural Network with Layer Skipping Strategy,” in Proceedings of the IEEE 6th International Conference on Industrial Engineering and Applications, Tokyo, pp. 475- 479, 2019. https://doi.org/10.1109/IEA.2019.8715122

[2] Awang S., Azmi N., and Rahman A., “Vehicle Type Classification using an Enhanced Sparse- Filtered Convolutional Neural Network with Layer-Skipping Strategy,” IEEE Access, vol. 8, pp. 14265-14277, 2020. https://doi.org/10.1109/ACCESS.2019.2963486

[3] Chiang C., Jaber M., Chai K., and Loo J., “Distributed Acoustic Sensor Systems for Vehicle Detection and Classification,” IEEE Access, vol. 11, pp. 31293-31303, 2023. https://doi.org/10.1109/ACCESS.2023.3260780

[4] Dong Z., Wu Y., Pei M., and Jia Y., “Vehicle Type Classification Using a Semisupervised Convolutional Neural Network,” IEEE Transactions on Intelligent Transportation Systems, vol. 16, pp. 2247-2256, 2015. https://doi.org/10.1109/TITS.2015.2402438

[5] Elassy M., Al-Hattab M., Takruri M., and Badawi S., “Intelligent Transportation Systems for Sustainable Smart Cities,” Transportation Engineering, vol. 16, pp. 100252, 2024. https://doi.org/10.1016/j.treng.2024.100252

[6] Lin K., Zhao H., Lv J., Zhan J., and et al., “Face Detection and Segmentation with Generalized Intersection over Union based on Mask_RCNN,” in Proceedings of the 10th International Conference Advances in Brain Inspired Cognitive Systems, Guangzhou, pp. 106-116, 2020. https://doi.org/10.1007/978-3-030-39431-8_11

[7] Minkesh A., Worranitta K., and Taizo M., “Human Extraction and Scene Transition Utilizing Mask_RCNN,” arXiv Preprint, pp. 1-6, 2025. https://arxiv.org/abs/1907.08884v2

[8] Ojha A., Sahu S., and Dewangan D., “Vehicle Detection Through Instance Segmentation Using Mask_RCNN for Intelligent Vehicle System,” in Proceedings of the 5th International Conference on Intelligent Computing and Control Systems, Madurai, pp. 954-959, 2021. https://doi.org/10.1109/ICICCS51141.2021.9432 374

[9] Ojha G., Poudel D., Khanal J., and Pokhrel N., “Design and Analysis of Computer Vision Techniques for Object Detection and Recognition in ADAS,” Journal of Innovations in Engineering Education, vol. 5, pp. 47-58, 2022. https://doi.org/10.3126/jiee.v5i1.43682 24 The International Arab Journal of Information Technology, Vol. 23, No. 1, January 2026

[10] Qian Z., Zhao C., Zhang B., Lin S., and et al., “Classification of Vehicle Types using Fused Deep Convolutional Neural Networks,” Journal of Intelligent and Fuzzy Systems, vol. 42, pp. 5125- 5137, 2022. https://doi.org/10.3233/JIFS-211505

[11] Ramakrishnan D. and Radhakrishnan K., “Applying Deep Convolutional Neural Network Algorithm in the Cloud Autonomous Vehicles Traffic Model,” The International Arab Journal of Information Technology, vol. 19, no. 2, pp. 186- 194, 2022. DOI: 10.34028/iajit/19/2/5

[12] Satyanarayana G., Deshmukh P., and Das S., “Vehicle Detection and Classification with Spatio- Temporal Information Obtained from CNN,” Displays, vol. 75, pp. 102294, 2022. https://doi.org/10.1016/j.displa.2022.102294

[13] Shim K., Yoon S., Ko K., and Kim C., “Multi- Target Multi-Camera Vehicle Tracking for City- Scale Traffic Management,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, pp. 4193-4200, 2021. https://doi.org/10.1109/CVPRW53098.2021.0047 3

[14] Tahir H., Khan M., and Tariq M., “Performance Analysis and Comparison of Faster R-CNN, Mask_RCNN and ResNet50 for the Detection and Counting of Vehicles,” in Proceedings of the International Conference on Computing, Communication, and Intelligent Systems, Greater Noida, pp. 587-594, 2021. https://doi.org/10.1109/ICCCIS51004.2021.9397 079

[15] Tahir N., Bature U., Baba M., Abubakar K., and Yarima S., “Image Recognition Based Autonomous Driving: A Deep Learning Approach,” International Journal of Engineering and Manufacturing, vol. 10, pp. 11-19, 2020. https://doi.org/10.5815/ijem.2020.06.02

[16] Zhang B. and Zhang J., “A Traffic Surveillance System for Obtaining Comprehensive Information of the Passing Vehicles Based on Instance Segmentation,” IEEE Transactions on Intelligent Transportation Systems, vol. 22, pp. 7040-7055, 2020. https://doi.org/10.1109/TITS.2020.3001154

[17] Zhang L., Wang P., Li H., Li Z., and et al., “A Robust Attentional Framework for License Plate Recognition in the Wild,” IEEE Transactions on Intelligent Transportation Systems, vol. 22, pp. 6967-6976, 2020. https://doi.org/10.1109/TITS.2020.3000072

[18] Zhang Y., Huang Y., Yu S., and Wang L., “Cross- View Gait Recognition by Discriminative Feature Learning,” IEEE Transactions on Image Processing, vol. 29, pp. 1001-1015, 2019. https://doi.org/10.1109/TIP.2019.2926208