Open Access

A Robust Computer Vision Approach for Automated Identification of Nigerian Federal University Logos Based on MSER Descriptor Analysis and CNN-Driven Image Classification Model

https://doi.org/10.55640/ijctisn-v03i08-01

PDF

Dr. Kwame Asante ¹ , Dr. Akosua Mensah ¹ ,

⁴ Department of Computer Science University of Ghana, Legon, Ghana

⁴ Faculty of Information Technology Kwame Nkrumah University of Science and Technology (KNUST), Ghana

Abstract

Automated logo recognition has emerged as a significant research area in computer vision due to its applications in document authentication, institutional identification, digital archiving, and content-based image retrieval systems. This study proposes a robust hybrid framework for the automated identification of Nigerian Federal University logos by integrating Maximally Stable Extremal Region (MSER) descriptor analysis with a Convolutional Neural Network (CNN)-driven classification model. The research is motivated by the challenges of logo variability, intra-class similarity, illumination changes, and low-resolution image constraints commonly encountered in real-world academic and administrative datasets.

The proposed approach leverages MSER-based region detection for stable feature extraction followed by deep feature learning through CNN architectures to improve classification accuracy and generalization performance. The integration of classical feature-based detection and modern deep learning techniques provides a hybrid solution that enhances robustness under complex visual conditions. Prior research has demonstrated that MSER is highly effective in detecting stable regions in images (Matas et al., 2004), and its adaptation in logo detection pipelines has shown promising results in document analysis systems (Alaei & Delalandre, 2014). Furthermore, CNN-based architectures have consistently achieved superior performance in image recognition tasks due to their hierarchical feature extraction capabilities (Krizhevsky et al., 2017).

Experimental considerations suggest that combining MSER region proposals with CNN classification significantly reduces false positives and improves recognition precision in structured institutional logo datasets. The study contributes to advancing computer vision applications in educational domain recognition systems and provides a scalable framework for national-level institutional logo classification

Keywords

Computer Vision, Logo Recognition, MSER Descriptor, Convolutional Neural Networks

References

Alaei, A., & Delalandre, M. (2014). A complete logo detection/recognition system for document images. 2014 11th IAPR International Workshop on Document Analysis Systems, Tours, France.

Alsheikhy, A., Said, Y., & Barr, M. (2020). Logo Recognition with the Use of Deep Convolutionla Neural Network. Engineering, Technology & Applied Science Research,10(5), 6191-6194.

Bianco, S., Buzzelli, M., Mazzini, D., & Schettini, R. (2017). Deep learning for logo recognition. Neurocomputing, 23-30.

Brownlee, J. (2019). A Gentle Introduction to Computer Vision. Retrieved 22 November 2023 from https://machinelearningmastery.com/what-is-computer-vision/

Carvalho, P., Pereira, A., & Viana, P. (2021). Automatic tv logo identification for advertisement detection without prior data. Applied Sciences,11(16), 7494.

Chen, R., Jalal, M. A., Mihaylova, L. S., & Moore, R. K. (2018). Learning Capsules for Vehicle Logo Recognition. 2018 21st International Conference on Information Fusion (FUSION), 565-572.

Cheng, Z.-Q., Wu, X., Liu, Y., & Hua, X.-S. (2017). Video ecommerce++: Toward large scale online video advertising. IEEE transactions on multimedia,19(6), 1170-1183.

Dixit, U. D., & Shirdhonkar, M. (2016). Automatic logo detection and extraction using singular value decomposition. 2016 International Conference on Communication and Signal Processing (ICCSP), Melmaruvathur, India.

Donoser, M., & Bischof, H. (2006). Efficient maximally stable extremal region (MSER) tracking. 2006 IEEE computer society conference on computer vision and pattern recognition (CVPR'06), New York, NY, USA.

Fehérvári, I., & Appalaraju, S. (2018). Scalable Logo Recognition Using Proxies. 2019 IEEE Winter Conference on Applications of Computer Vision (WACV), 715-725.

Hendrick, Wang, C.-M., Aripriharta, Jhe, C.-G., Tsu, P.-C., & Jong, G.-J. (2018). The halal logo classification by using NVIDIA DIGITS. 2018 International Conference on Applied Information Technology and Innovation (ICAITI), Padang, Indonesia.

Ho, D., Liang, E., & Liaw, R. (2019). 1000x Faster Data Augmentation. https://bair.berkeley.edu/blog/2019/06/07/data_aug/

Hou, S., Li, J., Min, W., Hou, Q., Zhao, Y., Zheng, Y., & Jiang, S. (2023). Deep learning for logo detection: A survey. ACM Transactionson Multimedia Computing, Communications and Applications,20(3), 1-23.

Irhebhude, M. E. (2015). Object detection, recognition and re-identification in video footage Loughborough University].

Kosala, G., Harjoko, A., & Hartati, S. (2023). MSER-Vertical Sobel for Vehicle Logo Detection. Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), 7(5), 1239-1245.

Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017). ImageNet Classification with Deep Convolutional Neural Networks. COMMUNICATIONS OF THE ACM, 60(6).

Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S. E., Fu, C.-Y., & Berg, A. C. (2015). SSD: Single Shot MultiBox Detector. European Conference on Computer Vision,

Llorca, D. F., Arroyo, R., & Sotelo, M. A. (2013). Vehicle logo recognition in traffic images using HOG features and SVM. 16th International IEEE Conference on Intelligent Transportation Systems (ITSC 2013), The Hague, The Netherlands.

Manger, D., Müller, M., & Kubietziel, M. (2015). Filtering local features for logo detection and localization in sports videos. 2015 IEEE International Conference on Signal and Image Processing Applications (ICSIPA), Kuala Lumpur, Malaysia.

Matas, J., Chum, O., Urban, M., & Pajdla, T. (2004). Robust wide-baseline stereo from maximally stable extremal regions. Image and vision computing, 22(10), 761-767.

Pan, D., Shi, P., Qiu, Z., Sha, Y., Zhongdi, X., & Zhoushao, J. (2016). TV Logo Classification Based on Convolutional neural network. International Conference on Information and Automation Ningbo, China.

Pimkote, P., & Kangkachit, T. (2018). Classification of alcohol brand logos using convolutional neural networks. 2018 International Conference on Digital Arts, Media and Technology (ICDAMT), Phayao, Thailand.

Ren, S., He, K., Girshick, R. B., & Sun, J. (2015). Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39, 1137-1149.

Sharma, N., Mandal, R., Sharma, R., Pal, U., & Blumenstein, M. (2018). Signature and Logo Detection using Deep CNN for Document Image Retrieval. 2018 16th International Conference on Frontiers in Handwriting Recognition (ICFHR), 416-422.

Wang, Y., Yang, W., & Zhang, H. (2018). Deep learning single logo recognition with data enhancement by shape context. 2018 International Joint Conference on Neural Networks (IJCNN), Rio de Janeiro, Brazil.

Yousaf, W., Umar, A., Shirazi, S. H., Khan, Z., Razzak, I., & Zaka, M. (2021). Patch-CNN: Deep learning for logo. Journal of Intelligent & Fuzzy Systems, 3849–3862.

Yu, Y., Guan, H., Li, D., & Yu, C. (2019). A cascaded deep convolutional network for vehicle logo recognition from frontal and rear images of vehicles. IEEE Transactions on Intelligent Transportation Systems, 22(2), 758-771.

Yufeng, D., & Bo, Z. (2018). Intelligent identification method of bicycle logo based on Haar classifier. 2018 5th International Conference on Systems and Informatics (ICSAI),

Zulkeefli, S. N. I., & Hashim, N. (2022). Comparison of CNN-based Algorithms for Halal Logo Recognition. Journal of System and Management Sciences, 12(5), 155-168.

Most read articles by the same author(s)

1 2 3 4 5 6 7 > >>

International Journal of Cyber Threat Intelligence and Secure Networking

A Robust Computer Vision Approach for Automated Identification of Nigerian Federal University Logos Based on MSER Descriptor Analysis and CNN-Driven Image Classification Model

Abstract

Keywords

References

Most read articles by the same author(s)

Similar Articles