Multi-PIE Ear Dataset

This dataset was generated from Multi-PIE face dataset [1, 2]. In this repository, we just published image name from Multi-PIE face dataset and detected ear coordinates. You can use face images and corresponding coordinates to obtain ear images.

This dataset has been explained and has been used in our paper. Please cite it, if it is helpful for you.

@article{eyiokur2017domain,
  title={Domain adaptation for ear recognition using deep convolutional neural networks},
  author={Eyiokur, Fevziye Irem and Yaman, Dogucan and Ekenel, Haz{\i}m Kemal},
  journal={IET Biometrics},
  volume={7},
  number={3},
  pages={199--206},
  year={2017},
  publisher={IET}
}

Dataset Info:

• Number of subject: 205
• Number of images: 17183

References

• [1] Gross, R., Matthews, I., Cohn, J.F., et al.: ‘Multi-PIE’. IEEE Int. Conf. on Automatic Face and Gesture Recognition (FG), 2008.
• [2] Gross, R., Matthews, I., Cohn, J.F., et al.: ‘Multi-PIE’. Image and Vision Computing, 2010, pp. 807–813.