Abstract
Deep learning has a hierarchical network architecture to represent the complicated feature of input patterns. We have developed the adaptive structure learning method of deep belief network (adaptive DBN) that can discover an optimal number of hidden neurons for given input data in a restricted Boltzmann machine (RBM) by neuron generation–annihilation algorithm and can obtain appropriate number of hidden layers in DBN. In this paper, our model is applied to Families in Wild Multimedia (FIW): A multi-modal database for recognizing kinship. The kinship verification is a problem whether two facial images have the blood relatives or not. In this paper, the two facial images are composed into one image to recognize kinship. The classification accuracy for the developed system became higher than the traditional method.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Proceedings of Advances in Neural Information Processing Systems 25 (NIPS 2012) (2012)
Szegedy, C., Liu, W., et.al.: Going deeper with convolutions. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.1–9 (2015)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: Proceedings of International Conference on Learning Representations (ICLR 2015) (2015)
He, K., Zhang, X., en, S.R., Sun, J.: Deep residual learning for image recognition. In: Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.770–778 (2016)
Hinton, G.E., Osindero, S., Teh, Y.: A fast learning algorithm for deep belief nets. Neural Comput. 18(7), 1527–1554 (2006)
Hinton, G.E.: A Practical Guide to Training Restricted Boltzmann Machines, Neural Networks, Tricks of the Trade, Lecture Notes in Computer Science (LNCS, vol. 7700), pp.599–619 (2012)
Kamada, S., Ichimura, T.: An adaptive learning method of restricted Boltzmann machine by neuron generation and annihilation algorithm. In: Proceedings of 2016 IEEE International Conference on Systems, Man, and Cybernetics (IEEE SMC 2016), pp. 1273–1278 (2016)
Kamada, S., Ichimura, T.: An adaptive learning method of deep belief network by layer generation algorithm. In: Proceedings of IEEE TENCON2016, pp. 2971–2974 (2016)
Krizhevsky, A.: Learning Multiple Layers of Features from Tiny Images, Master of thesis, University of Toronto (2009)
Kamada, S., Ichimura, T., Hara, A., Mackin, K.J.: Adaptive Structure Learning Method of Deep Belief Network using Neuron Generation-Annihilation and Layer Generation, Neural Computing and Applications, pp. 1–15 (2018)
Wang, S., Robinson, J.P., Fu, Y., Yun.: Kinship verification on families in the wild with marginalized denoising metric learning. In: 2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017), pp. 216–221 (2017)
Rachmadi, R.F., Purnama, I.K.E., Nugroho, S.M.S., Suprapto, Y.K.: Image-based Kinship verification using fusion convolutional neural network. In: Proceedings of 2019 IEEE 11th International Workshop on Computational Intelligence and Applications (IWCIA), pp. 59–65 (2019)
Robinson, J.P., Shao, M., Wu, Y., Fu, Y.: Families in the wild (FIW): large-scale kinship image database and benchmarks. In: Proceedings of the 24th ACM International Conference on Multimedia, pp. 242–246 (2016)
Li, Y., Zeng, J., Zhang, J., Dai, A., Kan, M., Sham, S., Chem, X.: KinNet: fine-to-coarse deep metric learning for kinship verification. In: Proceedings of the 2017 Workshop on Recognizing Families in the Wild, pp. 13–20 (2017)
Kamada, S., Ichimura, T.: Fine tuning of adaptive learning of deep belief network for misclassification and its knowledge acquisition. Int. J. Comput. Intell. Stud. 6(4), 333–348 (2017)
Kamada, S., Ichimura, T., Harada, T.: Knowledge extraction of adaptive structural learning of deep belief network for medical examination data. Int. J. Semant. Comput. 13(1), 67–86 (2019)
Ichimura, T., Kamada, S.: A distillation learning model of adaptive structural deep belief network for affectnet: facial expression image database. In: Proceedings of the 9th International Congress on Advanced Applied Informatics (IIAI AAI 2020), pp. 454–459 (2020)
Acknowledgements
This work was supported by JSPS KAKENHI Grant Number 19K12142, 19K24365 and obtained from the commissioned research by National Institute of Information and Communications Technology (NICT, 21405), Japan.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Ichimura, T., Kamada, S. (2021). Adaptive Structural Deep Learning to Recognize Kinship Using Families in Wild Multimedia. In: Czarnowski, I., Howlett, R.J., Jain, L.C. (eds) Intelligent Decision Technologies. Smart Innovation, Systems and Technologies, vol 238. Springer, Singapore. https://doi.org/10.1007/978-981-16-2765-1_46
Download citation
DOI: https://doi.org/10.1007/978-981-16-2765-1_46
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-2764-4
Online ISBN: 978-981-16-2765-1
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)