Multi-Region Ensemble Convolutional Neural Network for High Accuracy Age Estimation

Yiliang Chen, zichang Tan, Alex Po Leung, Jun Wan and Jianguo Zhang

Abstract

In real life, when telling a person’s age from his/her face, we tend to look at his/her whole face first and then focus on certain important regions like eyes. After that we will focus on each particular facial feature individually like the nose or the mouth so that we can decide the age of the person. Similarly, in this paper, we propose a new framework for age estimation, which is based on human face sub-regions. Each sub-network in our framework takes the input of two images each from human facial region. One of them is the global face, and the other is a vital sub-region. Then, we combine the predictions from different sub-regions based on a majority voting method. We call our framework Multi-Region Network Prediction Ensemble (MRNPE) and evaluate our approach using two popular public datasets: MORPH Album II and Cross Age Celebrity Dataset (CACD). Experiments show that our method outperforms the existing state-of-the-art age estimation methods by a significant margin. The Mean Absolute Errors (MAE) of age estimation are dropped from 3.03 to 2.73 years on the MORPH Album II and 4.79 to 4.

Session

Posters

Files

PDF iconPaper (PDF)

DOI

10.5244/C.31.176
https://dx.doi.org/10.5244/C.31.176

Citation

Yiliang Chen, zichang Tan, Alex Po Leung, Jun Wan and Jianguo Zhang. Multi-Region Ensemble Convolutional Neural Network for High Accuracy Age Estimation. In T.K. Kim, S. Zafeiriou, G. Brostow and K. Mikolajczyk, editors, Proceedings of the British Machine Vision Conference (BMVC), pages 176.1-176.12. BMVA Press, September 2017.

Bibtex

            @inproceedings{BMVC2017_176,
                title={Multi-Region Ensemble Convolutional Neural Network for High Accuracy Age Estimation},
                author={Yiliang Chen, zichang Tan, Alex Po Leung, Jun Wan and Jianguo Zhang},
                year={2017},
                month={September},
                pages={176.1-176.12},
                articleno={176},
                numpages={12},
                booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
                publisher={BMVA Press},
                editor={Tae-Kyun Kim, Stefanos Zafeiriou, Gabriel Brostow and Krystian Mikolajczyk},
                doi={10.5244/C.31.176},
                isbn={1-901725-60-X},
                url={https://dx.doi.org/10.5244/C.31.176}
            }