Classification of Different Age Groups of People by Using Deep Learning
Abstract
The Purpose of this study is to classify human images of different age groups with VggNet which is one of the Deep Learning (DL) models. Artificial intelligence, machine learning and computer vision have been carried out in recent years at very advanced level. Undoubtedly, it is a great contribution of DL in the rapid progress of these studies. Although DL foundational is based on past history, it has become popular in the imageNet competition held in 2012. This is because the top-5 error rate of 26.1% for visual object description has fallen to 15.3% for the first time with a sharp decline that year with DL. The Convolution Neural Network (CNN) is basis of DL models. It is basically composed of 4 layers. These are Convolution Layer, ReLu Layer, Pooling Layer and Full Connected Layer. DL models are designed using different numbers of these layers. In this study, people are divided into 12 classes according to age groups. These classes are man, woman, man face, woman face, old man, old woman, old man face, old woman face, boy, girl, boy face, girl face respectively. A new data set was created for people in 12 different age categories. For Each class 150 and totally 1800 images were collected. 90% of these images were used for training and the remaining 10% were used for testing. VggNet was trained with this data set. As a result of the study, it was seen that people in different age groups were estimated with 78.5% accuracy with VggNet model. DL models need to be trained with large data required. But it has been seen that training success has achieved a certain value with little data.
Keywords
References
- Ahmed, E., Jones, M., Marks, T.K., 2015. An improved deep learning architecture for person re-identification, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3908-3916.
- Amodei, D., Ananthanarayanan, S., Anubhai, R., Bai, J., Battenberg, E., Case, C., Casper, J., Catanzaro, B., Cheng, Q., Chen, G., 2016. Deep speech 2: End-to-end speech recognition in english and mandarin, International Conference on Machine Learning, pp. 173-182.
- Bahdanau, D., Chorowski, J., Serdyuk, D., Brakel, P., Bengio, Y., 2016. End-to-end attention-based large vocabulary speech recognition, Acoustics, Speech and Signal Processing (ICASSP), 2016 IEEE International Conference on. IEEE, pp. 4945-4949.
- Bengio, Y., Courville, A., Vincent, P., 2013. Representation Learning: A Review and New Perspectives. Ieee T Pattern Anal 35, 1798-1828.
- Deshpande, A., 2018. https://adeshpande3.github.io/adeshpande3.github.io/The-9-Deep-Learning-Papers-You-Need-To-Know-About.html.
- Graves, A., Mohamed, A.-r., Hinton, G., 2013. Speech recognition with deep recurrent neural networks, Acoustics, speech and signal processing (icassp), 2013 ieee international conference on. IEEE, pp. 6645-6649.
- Hermann, K.M., Kocisky, T., Grefenstette, E., Espeholt, L., Kay, W., Suleyman, M., Blunsom, P., 2015. Teaching machines to read and comprehend, Advances in Neural Information Processing Systems, pp. 1693-1701.
- Heuritech, 2018. https://blog.heuritech.com/2016/02/29/a-brief-report-of-the-heuritech-deep-learning-meetup-5/.
- Hinton, G., Deng, L., Yu, D., Dahl, G.E., Mohamed, A.-r., Jaitly, N., Senior, A., Vanhoucke, V., Nguyen, P., Sainath, T.N., 2012. Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups. IEEE Signal Processing Magazine 29, 82-97.
- Jozefowicz, R., Vinyals, O., Schuster, M., Shazeer, N., Wu, Y., 2016. Exploring the limits of language modeling. arXiv preprint arXiv:1602.02410.