Optimization and Comprehensive Application of ORB Algorithm and CNN Combined in Feature Extraction

Kefei Wu

doi:10.54097/75h32h45

Authors

Kefei Wu

DOI:

https://doi.org/10.54097/75h32h45

Keywords:

ORB algorithm, Convolutional Neural Network (CNN), Feature extraction, Fusion methods, Feature-level fusion, Decision-level fusion, Lightweight model

Abstract

In recent years, an increasing number of studies have attempted to combine ORB with CNN to achieve both efficiency and high accuracy. This survey, based on existing literature, systematically organizes typical fusion methods, application cases, optimization strategies, and challenges of ORB+CNN, and discusses future research trends in this direction. All literature used in this survey comes from published research results, including representative studies of ORB and CNN in fields such as iris recognition, clothing retrieval, vehicle classification, and SDN traffic classification.

Downloads

Download data is not yet available.

References

[1] Chen, Y., Cheng, W., & Wang, Y. (2020). T-center: A novel feature extraction approach towards large-scale Iris recognition. IEEE Access, 8, 32365–32375.

https://doi.org/10.1109/ACCESS.2020.2973601

[2] Babu, G., & Khayum, P. A. (2022). Elephant herding with whale optimization enabled ORB features and CNN for Iris recognition. Multimedia Tools and Applications, 81, 5761–5794. https://doi.org/10.1007/s11042-021-11821-z

[3] Kaur, B., & Saini, S. S. (2024). ContactLensIris: A robust iris recognition system based on integrated deep learning approach. 2024 International Conference on Electrical Electronics and Computing Technologies (ICEECT), 1–5. https://doi.org/10.1109/ICEECT61758.2024.10739228

[4] Martinez, L., Rivera, M. M., Zezatti, A. O., Ponce, J., & Guzman, E. (2025). Web-based clothing searcher utilizing convolutional neural networks and dissimilarity rules for color classification in the HSL color space and ORB algorithm for garment characterization. International Journal of Combinatorial Optimization Problems and Informatics, 16(3), 118–132.

[5] Yusuf, M. O., Hanzla, M., & Jalal, A. (2024). Vehicle detection and classification via YOLOv4 and CNN over aerial images. 2024 International Conference on Engineering & Computing Technologies (ICECT), 1–6. https://doi.org/10.1109/ICECT61618.2024.10581252

[6] Yzzogh, H., & Benaboud, H. (2025). Evaluating ORB and SIFT with neural network as alternatives to CNN for traffic classification in SDN environments. IEEE Access, 13, 47986–48001. https://doi.org/10.1109/ACCESS.2025.3553449