NIGERIAN ETHNICITY CLASSIFICATION THROUGH FUSED FEATURES FROM MOBILENET-V2 AND LOCAL BINARY PATTERN GUIDED BY ATTENTION MECHANISM

Authors

Keywords:

Ethnicity Classification, Computer Vision, MobileNetV2, Local Binary Patterns, Attention mechanism

Abstract

Our face plays a vital role in many human-to-human encounters and is closely linked to our identity. Significant promise exists for the automatic recognition of facial features, opening the door to hands-free alternatives and innovative uses in computer-human digital interactions. Deep learning techniques have led to a notable increase in interest in the field of face picture analysis in recent years, especially in applications like biometrics, security, and surveillance. Due to feature overlaps and dataset under-representation, ethnicity classification in computer vision is still a difficult task, particularly for African populations. This study explores Nigerian ethnicity classification, focusing on the three major groups—Hausa, Igbo, and Yoruba—using a hybrid model that integrates MobileNetV2, Local Binary Patterns (LBP), and an Attention Mechanism. The hybrid model achieved an overall classification accuracy of 87%, significantly outperforming benchmarks, particularly in Igbo and Yoruba classifications. While the Yoruba group demonstrated the highest accuracy, overlaps between Hausa and Igbo highlight areas for refinement. This research advances the field by addressing dataset imbalances, incorporating innovative feature fusion, and improving the inclusivity of computer vision models. It has practical implications for identity verification, security, and demographic research while emphasizing the importance of culturally sensitive AI systems tailored to underrepresented populations. Future work includes expanding datasets, enhancing model architectures, and exploring interdisciplinary approaches to further refine ethnicity classification.

Dimensions

Ahmed A Khan M Qureshi A 2022 CBAM in Multimodal Transformers for Caption Generation Neural Networks 142 98109

Aina S Adeniji M O Lawal A R Oluwaranti A I 2022 Development of a convolutional neural networkbased ethnicity classification model from facial images

AlHumaidan N A Prince M 2021 A classification of Arab ethnicity based on face image using deep learning approach IEEE Access 9 5075550766

Anwar I Ul Islam N 2017 Learned features are better for ethnicity classification arXiv preprint arXiv170907429

Chandaliya M Patel J Ahmed S 2024 Efficient spatial feature learning for ethnicity classification Advanced AI Systems 181 7885

Chen H Zhang Y Lin D 2022 Ethnicity recognition via large pretrained models AR5IV Papers with Code Retrieved from httpsar5ivlabsarxivorg

Chen W Zhang Y Zhao H Yang J 2021 CBAMEnhanced GANs for Image Generation Neurocomputing 450 110123

Chowdhury N et al 2020 Intersectionality in facial analysis systems Computer Vision Journal 348 910920

Cole J B Manyama M Larson J R Liberton D K Ferrara T M Riccardi S L Spritz R A 2017 Human facial shape and size heritability and genetic correlations Genetics 2052 967978

Digante S 2021 Exploring advancements in facial ethnicity classification using deep learning IEEE Transactions on Biometrics

Feng J et al 2023 Adversarial debiasing in ethnicity recognition Journal of AI Ethics 452 567582

Gad A R Nashat A A Barkat T M 2021 Intrusion detection system using machine learning for vehicular ad hoc networks based on ToNIoT dataset IEEE Access 9 142206142217

Gao H et al 2022 Developed ethnicity recognition systems using adversarial training to mitigate racial bias in datasets

Heng Z Dipu M Yap K H 2018 Hybrid supervised deep learning for ethnicity classification using face images In 2018 IEEE International Symposium on Circuits and Systems ISCAS pp 15 IEEE

Heydarian M Doyle T E Samavi R 2022 MLCM Multilabel confusion matrix IEEE

Howard L Yang X Gupta P 2023 Bias in commercial face recognition systems AR5IV Papers with Code Retrieved from httpsar5ivlabsarxivorg

Hu J Shen L Sun G 2020 SqueezeandExcitation Networks with CBAM for Medical Image Segmentation IEEE Transactions on Medical Imaging 393 770780

Iqbal S Qureshi A N Mustafa G 2022 Hybridization of CNN with LBP for classification of melanoma images Computers Materials Continua 713

Jilani S K Ugail H Bukar A M Logan A 2019 On the ethnic classification of Pakistani face using deep learning In 2019 International Conference on Cyberworlds CW pp 191198 IEEE

Khan K Khan R U Ali J Uddin I Khan S Roh B H 2021 Race classification using deep learning Computers Materials Continua 683

Kumar R Sen A Lee T 2023 Skin tone normalization for inclusive datasets AR5IV Papers with Code Retrieved from httpsar5ivlabsarxivorg

Lakshmiprabha N S 2016 Face image analysis using aam gabor lbp and wd features for gender age expression and ethnicity classification arXiv preprint arXiv160401684

Makolo A U Dada O V 2023 Ethnicity classification A machine learning approach Egyptian Computer Science Journal 471

Masood S Gupta S Wajid A Gupta S Ahmed M 2018 Prediction of human ethnicity from facial images using neural networks In Data Engineering and Intelligent Computing Proceedings of IC3T 2016 pp 217226 Springer Singapore

Mubarak A S Serte S AlTurjman F Ameen Z S I Ozsoz M 2022 Local binary pattern and deep learning feature extraction fusion for COVID19 detection on computed tomography images Expert Systems 393 e12842

Mustapha M F Mohamad N M Osman G Ab Hamid S H 2021 Age group classification using convolutional neural network CNN In Journal of Physics Conference Series Vol 2084 No 1 p 012028 IOP Publishing

Nguyen H et al 2021 Selfsupervised learning for ethnicity classification IEEE Access 9 112345112355

Obayya M Alotaibi S S Dhahb S Alabdan R Al Duhayyim M Hamza M A Motwakel A 2022 Optimal deep transfer learningbased ethnicity recognition on face images Image and Vision Computing 128 104584

Patel K et al 2022 Forensic applications of ethnicity recognition Neural Computing Applications 405 23452356

Platanios E Poon H Mitchell T M Horvitz E J 2017 Estimating accuracy from unlabeled data A probabilistic logic approach In Advances in Neural Information Processing Systems 30

Ranjan R Sankaranarayanan S Bansal A Bodla N Chen J C Patel V M Chellappa R 2018 Deep learning for understanding faces Machines may be just as good or better than humans IEEE Signal Processing Magazine 351 6683

Razalli H Alkawaz M H 2019 Realtime face tracking application with embedded facial age range estimation algorithm In 2019 IEEE 9th International Conference on System Engineering and Technology ICSET pp 471476 IEEE

Reference Gao H et al 2022 Adversarial training for bias reduction in ethnicity recognition Neural Computing Applications 346 45014515

Russakovsky O Deng J Su H Krause J Satheesh S Ma S FeiFei L 2015 ImageNet large scale visual recognition challenge International Journal of Computer Vision 115 211252

SantamariaGranados L MunozOrganero M RamirezGonzalez G Abdulhay E Arunkumar N J 2018 Using deep convolutional neural network for emotion detection on a physiological signals dataset AMIGOS IEEE Access 7 5767

SantamariaGranados L MunozOrganero M RamirezGonzalez G Abdulhay E 2022

Smith J Jones P Patel R 2023 Ethical considerations in ethnicity classification AI and Society 384 12311245

Suresh H Guttag J V 2022 Mitigating biases in demographic classification systems MDPI Journal of Bias Studies

Tan Y Liu X Chen T 2020 Spatiotemporal convolutional neural network with convolutional block attention module for microexpression recognition Information 118 380 httpsdoiorg103390info11080380

Tsalakanidou F et al 2021 Hybrid models for ethnicity recognition Advances in AI Applications

Wang X Liu Y Zhao J 2021 Transfer learning in ethnicity classification Neurocomputing 456 7890

Woo S Park J Lee J Kweon I S 2018 CBAM Convolutional Block Attention Module European Conference on Computer Vision ECCV Retrieved from httpsarxivorgabs180706521

Wu H et al 2023 Enhancing fairness in ethnicity recognition through dataset augmentation Journal of Computational Vision

Wu X Yuan P Wang T Gao D Cai Y 2018 Race classification from face using deep convolutional neural networks In 2018 3rd International Conference on Advanced Robotics and Mechatronics ICARM pp 16 IEEE

Zhou Y et al 2022 Integrating 2D and 3D features for robust ethnicity classification Computer Vision and Pattern Recognition

Published

31-12-2024

How to Cite

NIGERIAN ETHNICITY CLASSIFICATION THROUGH FUSED FEATURES FROM MOBILENET-V2 AND LOCAL BINARY PATTERN GUIDED BY ATTENTION MECHANISM. (2024). FUDMA JOURNAL OF SCIENCES, 8(6), 367-379. https://doi.org/10.33003/fjs-2024-0806-2973

Issue

Vol. 8 No. 6 (2024): FUDMA Journal of Sciences - Vol. 8 No. 6 (Special Issue)

Section

Research Articles
Copyright & Licensing

FUDMA Journal of Sciences

How to Cite

NIGERIAN ETHNICITY CLASSIFICATION THROUGH FUSED FEATURES FROM MOBILENET-V2 AND LOCAL BINARY PATTERN GUIDED BY ATTENTION MECHANISM. (2024). FUDMA JOURNAL OF SCIENCES, 8(6), 367-379. https://doi.org/10.33003/fjs-2024-0806-2973

Most read articles by the same author(s)