Predição Estruturada de Posições Anatômicas em Conjuntos Decadactilares
Resumo
A classificação precisa da posição anatômica a partir de imagens de impressões digitais desempenha um papel crítico em sistemas biométricos de identificação civil. Contudo, rótulos ausentes ou inconsistentes degradam severamente a indexação. Métodos atuais classificam as impressões isoladamente, ignorando a ocorrência única de cada posição no conjunto decadactilar. O método proposto neste trabalho integra Redes Neurais Convolucionais à otimização por atribuição linear para calcular uma atribuição globalmente consistente das dez impressões. Avaliada na base SOCOFing com múltiplas arquiteturas, a classificação independente produz baixa consistência por indivíduo (13,3%). O método proposto eleva essa métrica para 60,0%, mitigando as limitações da classificação isolada.Referências
Al-Wajih, Y. A., Hamanah, W. M., Abido, M. A., Al-Sunni, F., and Alwajih, F. (2022). Finger type classification with deep convolution neural networks. In ICINCO, pages 247–254.
Giudice, O., Litrico, M., and Battiato, S. (2020). Single architecture and multiple task deep neural network for altered fingerprint analysis. In 2020 IEEE International Conference on Image Processing (ICIP), pages 813–817.
Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning. MIT Press.
He, K., Zhang, X., Ren, S., and Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778.
Hsiao, C. T., Lin, C. Y., Wang, P. S., and Wu, Y. T. (2022). Application of convolutional neural network for fingerprint-based prediction of gender, finger position, and height. Entropy, 24.
Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K. Q. (2017). Densely connected convolutional networks. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 2261–2269.
Iloanusi, O. N. and Ejiogu, U. C. (2020). Gender classification from fused multi-fingerprint types. Information Security Journal: A Global Perspective, 29(5):209–219.
Jain, A. K., Ross, A. A., Nandakumar, K., and Swearingen, T. (2025). Introduction to Biometrics. Springer International Publishing, Cham.
Jian, W., Zhou, Y., and Liu, H. (2020). Lightweight convolutional neural network based on singularity roi for fingerprint classification. IEEE Access, 8:54554–54563.
Kim, J., Rim, B., Sung, N.-J., and Hong, M. (2020). Left or right hand classification from fingerprint images using a deep neural network. Computers, Materials & Continua, 63(1).
Loshchilov, I. and Hutter, F. (2017). Decoupled weight decay regularization. arXiv pre-print arXiv:1711.05101.
Maiti, D., Basak, M., and Das, D. (2024). Deep learning method for multi-attribute analysis of fingerprint images. Computer Science Journal of Moldova, 32(2).
Maltoni, D., Maio, D., Jain, A. K., and Feng, J. (2022). Handbook of Fingerprint Recognition. Springer Cham, 3rd edition.
Michelsanti, D., Ene, A. D., Guichi, Y., Stef, R., Nasrollahi, K., and Moeslund, T. B. (2017). Fast fingerprint classification with deep neural networks. In VISIGRAPP 2017 - Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, volume 5, pages 202–209. SciTe-Press.
Militello, C., Rundo, L., Vitabile, S., and Conti, V. (2021). Fingerprint classification based on deep learning approaches: Experimental findings and comparisons. Symmetry, 13.
Oleiwi, B. K., Abood, L. H., and Farhan, A. K. (2022). Integrated different fingerprint identification and classification systems based deep learning. In 2022 International Conference on Computer Science and Software Engineering (CSASE), pages 188–193.
Pessach, D., Singer, G., Avrahami, D., Chalutz Ben-Gal, H., Shmueli, E., and Ben-Gal, I. (2020). Employees recruitment: A prescriptive analytics approach via machine learning and mathematical programming. Decision Support Systems, 134:113290.
Pillai, R., Sharma, N., Upadhyay, D., Dangi, S., and Gupta, R. (2024). Precision in biometric authentication: Cnn-driven fingerprint classification. In 2024 3rd International Conference for Innovation in Technology (INOCON), pages 1–5.
Rim, B., Kim, J., and Hong, M. (2021). Fingerprint classification using deep learning approach. Multimedia Tools and Applications, 80:35809–35825.
Shehu, Y. I., Ruiz-Garcia, A., Palade, V., and James, A. (2018a). Detailed identification of fingerprints using convolutional neural networks. In Proceedings - 17th IEEE International Conference on Machine Learning and Applications, ICMLA 2018, pages 1161–1165. Institute of Electrical and Electronics Engineers Inc.
Shehu, Y. I., Ruiz-Garcia, A., Palade, V., and James, A. (2018b). Sokoto coventry fingerprint dataset. arXiv preprint arXiv:1807.10609.
Simonyan, K. and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.
Singh, T., Bhisikar, S., Satakshi, and Kumar, M. (2021). Fingerprint identification using modified capsule network. In 2021 12th International Conference on Computing Communication and Networking Technologies (ICCCNT), pages 1–6.
Tan, M. and Le, Q. (2019). Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning, pages 6105–6114. PMLR.
United Nations (UN) (1948). Universal Declaration of Human Rights. UN General Assembly Resolution 217 A (III). Adopted on December 10, 1948.
Win, K. N., Li, K., Chen, J., Viger, P. F., and Li, K. (2020). Fingerprint classification and identification algorithms for criminal investigation: A survey. Future Generation Computer Systems, 110:758–771.
Yosinski, J., Clune, J., Bengio, Y., and Lipson, H. (2014). How transferable are features in deep neural networks? Advances in neural information processing systems, 27.
Zhong, Z., Zheng, L., Kang, G., Li, S., and Yang, Y. (2020). Random erasing data augmentation. In Proceedings of the AAAI conference on artificial intelligence, volume 34, pages 13001–13008.
Giudice, O., Litrico, M., and Battiato, S. (2020). Single architecture and multiple task deep neural network for altered fingerprint analysis. In 2020 IEEE International Conference on Image Processing (ICIP), pages 813–817.
Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning. MIT Press.
He, K., Zhang, X., Ren, S., and Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778.
Hsiao, C. T., Lin, C. Y., Wang, P. S., and Wu, Y. T. (2022). Application of convolutional neural network for fingerprint-based prediction of gender, finger position, and height. Entropy, 24.
Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K. Q. (2017). Densely connected convolutional networks. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 2261–2269.
Iloanusi, O. N. and Ejiogu, U. C. (2020). Gender classification from fused multi-fingerprint types. Information Security Journal: A Global Perspective, 29(5):209–219.
Jain, A. K., Ross, A. A., Nandakumar, K., and Swearingen, T. (2025). Introduction to Biometrics. Springer International Publishing, Cham.
Jian, W., Zhou, Y., and Liu, H. (2020). Lightweight convolutional neural network based on singularity roi for fingerprint classification. IEEE Access, 8:54554–54563.
Kim, J., Rim, B., Sung, N.-J., and Hong, M. (2020). Left or right hand classification from fingerprint images using a deep neural network. Computers, Materials & Continua, 63(1).
Loshchilov, I. and Hutter, F. (2017). Decoupled weight decay regularization. arXiv pre-print arXiv:1711.05101.
Maiti, D., Basak, M., and Das, D. (2024). Deep learning method for multi-attribute analysis of fingerprint images. Computer Science Journal of Moldova, 32(2).
Maltoni, D., Maio, D., Jain, A. K., and Feng, J. (2022). Handbook of Fingerprint Recognition. Springer Cham, 3rd edition.
Michelsanti, D., Ene, A. D., Guichi, Y., Stef, R., Nasrollahi, K., and Moeslund, T. B. (2017). Fast fingerprint classification with deep neural networks. In VISIGRAPP 2017 - Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, volume 5, pages 202–209. SciTe-Press.
Militello, C., Rundo, L., Vitabile, S., and Conti, V. (2021). Fingerprint classification based on deep learning approaches: Experimental findings and comparisons. Symmetry, 13.
Oleiwi, B. K., Abood, L. H., and Farhan, A. K. (2022). Integrated different fingerprint identification and classification systems based deep learning. In 2022 International Conference on Computer Science and Software Engineering (CSASE), pages 188–193.
Pessach, D., Singer, G., Avrahami, D., Chalutz Ben-Gal, H., Shmueli, E., and Ben-Gal, I. (2020). Employees recruitment: A prescriptive analytics approach via machine learning and mathematical programming. Decision Support Systems, 134:113290.
Pillai, R., Sharma, N., Upadhyay, D., Dangi, S., and Gupta, R. (2024). Precision in biometric authentication: Cnn-driven fingerprint classification. In 2024 3rd International Conference for Innovation in Technology (INOCON), pages 1–5.
Rim, B., Kim, J., and Hong, M. (2021). Fingerprint classification using deep learning approach. Multimedia Tools and Applications, 80:35809–35825.
Shehu, Y. I., Ruiz-Garcia, A., Palade, V., and James, A. (2018a). Detailed identification of fingerprints using convolutional neural networks. In Proceedings - 17th IEEE International Conference on Machine Learning and Applications, ICMLA 2018, pages 1161–1165. Institute of Electrical and Electronics Engineers Inc.
Shehu, Y. I., Ruiz-Garcia, A., Palade, V., and James, A. (2018b). Sokoto coventry fingerprint dataset. arXiv preprint arXiv:1807.10609.
Simonyan, K. and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.
Singh, T., Bhisikar, S., Satakshi, and Kumar, M. (2021). Fingerprint identification using modified capsule network. In 2021 12th International Conference on Computing Communication and Networking Technologies (ICCCNT), pages 1–6.
Tan, M. and Le, Q. (2019). Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning, pages 6105–6114. PMLR.
United Nations (UN) (1948). Universal Declaration of Human Rights. UN General Assembly Resolution 217 A (III). Adopted on December 10, 1948.
Win, K. N., Li, K., Chen, J., Viger, P. F., and Li, K. (2020). Fingerprint classification and identification algorithms for criminal investigation: A survey. Future Generation Computer Systems, 110:758–771.
Yosinski, J., Clune, J., Bengio, Y., and Lipson, H. (2014). How transferable are features in deep neural networks? Advances in neural information processing systems, 27.
Zhong, Z., Zheng, L., Kang, G., Li, S., and Yang, Y. (2020). Random erasing data augmentation. In Proceedings of the AAAI conference on artificial intelligence, volume 34, pages 13001–13008.
Publicado
19/07/2026
Como Citar
SILVA, Saulo G. de Matos; PEDROSA, Glauco V..
Predição Estruturada de Posições Anatômicas em Conjuntos Decadactilares. In: SEMINÁRIO INTEGRADO DE SOFTWARE E HARDWARE (SEMISH), 53. , 2026, Gramado/RS.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 530-541.
ISSN 2595-6205.
DOI: https://doi.org/10.5753/semish.2026.20872.
