Publications

@inproceedings{UERC2023,

title = {The Unconstrained Ear Recognition Challenge 2023: Maximizing Performance and Minimizing Bias},

author = {Ziga Emersic and Tetsushi Ohki and Muku Akasaka and Takahiko Arakawa and Soshi Maeda and Masora Okano and Yuya Sato and Anjith George and Sébastien Marcel and Iyyakutti Iyappan Ganapathi and Syed Sadaf Ali and Sajid Javed and Naoufel Werghi and Selin Gök Işık and Erdi Sarıtaş and Hazim Kemal Ekenel and Valter Hudovernik and Jan Niklas Kolf and Fadi Boutros and Naser Damer and Geetanjali Sharma and Aman Kamboj and Aditya Nigam and Deepak Kumar Jain and Guillermo Cámara and Peter Peer and Vitomir Struc},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2023/09/CameraReady-234.pdf},

year  = {2023},

date = {2023-09-01},

booktitle = {IEEE International Joint Conference on Biometrics (IJCB 2023)},

pages = {1-10},

address = {Ljubljana, Slovenia},

abstract = {The paper provides a summary of the 2023 Unconstrained

Ear Recognition Challenge (UERC), a benchmarking

effort focused on ear recognition from images acquired

in uncontrolled environments. The objective of the challenge

was to evaluate the effectiveness of current ear recognition

techniques on a challenging ear dataset while analyzing

the techniques from two distinct aspects, i.e., verification

performance and bias with respect to specific demographic

factors, i.e., gender and ethnicity. Seven research

groups participated in the challenge and submitted

a seven distinct recognition approaches that ranged from

descriptor-based methods and deep-learning models to ensemble

techniques that relied on multiple data representations

to maximize performance and minimize bias. A comprehensive

investigation into the performance of the submitted

models is presented, as well as an in-depth analysis of

bias and associated performance differentials due to differences

in gender and ethnicity. The results of the challenge

suggest that a wide variety of models (e.g., transformers,

convolutional neural networks, ensemble models) is capable

of achieving competitive recognition results, but also

that all of the models still exhibit considerable performance

differentials with respect to both gender and ethnicity. To

promote further development of unbiased and effective ear

recognition models, the starter kit of UERC 2023 together

with the baseline model, and training and test data is made

available from: http://ears.fri.uni-lj.si/.},

keywords = {biometrics, competition, computer vision, deep learning, ear, ear biometrics, UERC 2023},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{KinEars,

title = {Kinship Verification from Ear Images: An Explorative Study with Deep Learning Models},

author = {Grega Dvoršak and Ankita Dwivedi and Vitomir Štruc and Peter Peer and Žiga Emeršič},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2022/03/Gregovi_Uhlji_Template-2.pdf},

year  = {2022},

date = {2022-04-21},

urldate = {2022-04-21},

booktitle = {International Workshop on Biometrics and Forensics (IWBF)},

pages = {1--6},

abstract = {The analysis of kin relations from visual data represents a challenging research problem with important real-world applications. However, research in this area has mostly been limited to the analysis of facial images, despite the potential of other physical (human) characteristics for this task. In this paper, we therefore study the problem of kinship verification from ear images and investigate whether salient appearance characteristics, useful for this task, can be extracted from ear data. To facilitate the study, we introduce a novel dataset, called KinEar, that contains data from 19 families with each family member having from 15 to 31 ear images. Using the KinEar data, we conduct experiments using a Siamese training setup and  5 recent deep learning backbones. The results of our experiments suggests that ear images  represent a viable alternative to other modalities for kinship verification, as 4 out of 5 considered  models reach a performance of over 60% in terms of the Area Under the Receiver Operating Characteristics (ROC-AUC). },

keywords = {biometrics, CNN, deep learning, ear, ear biometrics, kinear, kinship, kinship recognition, transformer},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{emervsivc2019unconstrained,

title = {The Unconstrained Ear Recognition Challenge 2019},

author = {Žiga Emeršič and A. Kumar S. V. and B. S. Harish and W. Gutfeter and J. N. Khiarak and A. Pacut and E. Hansley and M. Pamplona Segundo and S. Sarkar and H. Park and G. Pyo Nam and I. J. Kim and S.G. Sangodkar and U. Kacar and M. Kirci and L. Yuan and J. Yuan and H. Zhao and F. Lu and J. Mao and X. Zhang and D. Yaman and F. I. Eyiokur and K. B. Ozler and H. K. Ekenel and D. Paul Chowdhury and S. Bakshi and P. K. Sa and B. Majhni and P. Peer and V. Štruc},

url = {https://arxiv.org/pdf/1903.04143.pdf},

year  = {2019},

date = {2019-06-01},

booktitle = {International Conference on Biometrics (ICB 2019)},

journal = {arXiv preprint arXiv:1903.04143},

abstract = {This paper presents a summary of the 2019 Unconstrained Ear Recognition Challenge (UERC), the second in a series of group benchmarking efforts centered around the problem of person recognition from ear images captured in uncontrolled settings. The goal of the challenge is to assess the performance of existing ear recognition techniques on a challenging large-scale ear dataset and to analyze performance of the technology from various viewpoints, such as generalization abilities to unseen data characteristics, sensitivity to rotations, occlusions and image resolution and performance bias on sub-groups of subjects, selected based on demographic criteria, i.e. gender and ethnicity. Research groups from 12 institutions entered the competition and submitted a total of 13 recognition approaches ranging from descriptor-based methods to deep-learning models. The majority of submissions focused on ensemble based methods combining either representations from multiple deep models or hand-crafted with learned image descriptors. Our analysis shows that methods incorporating deep learning models clearly outperform techniques relying solely on hand-crafted descriptors, even though both groups of techniques exhibit similar behaviour when it comes to robustness to various covariates, such presence of occlusions, changes in (head) pose, or variability in image resolution. The results of the challenge also show that there has been considerable progress since the first UERC in 2017, but that there is still ample room for further research in this area.},

keywords = {biometrics, ear, ear recognitoin, uerc 2019},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{emervsivc2017training,

title = {Training convolutional neural networks with limited training data for ear recognition in the wild},

author = {Žiga Emeršič and Dejan Štepec and Vitomir Štruc and Peter Peer},

url = {https://arxiv.org/pdf/1711.09952.pdf},

year  = {2017},

date = {2017-05-01},

booktitle = {IEEE International Conference on Automatic Face and Gesture Recognition, Workshop on Biometrics in the Wild 2017},

journal = {arXiv preprint arXiv:1711.09952},

abstract = {Identity recognition from ear images is an active field of research within the biometric community. The ability to capture ear images from a distance and in a covert manner makes ear recognition technology an appealing choice for surveillance and security applications as well as related application domains. In contrast to other biometric modalities, where large datasets captured in uncontrolled settings are readily available, datasets of ear images are still limited in size and mostly of laboratory-like quality. As a consequence, ear recognition technology has not benefited yet from advances in deep learning and convolutional neural networks (CNNs) and is still lacking behind other modalities that experienced significant performance gains owing to deep recognition technology. In this paper we address this problem and aim at building a CNNbased ear recognition model. We explore different strategies towards model training with limited amounts of training data and show that by selecting an appropriate model architecture, using aggressive data augmentation and selective learning on existing (pre-trained) models, we are able to learn an effective CNN-based model using a little more than 1300 training images. The result of our work is the first CNN-based approach to ear recognition that is also made publicly available to the research community. With our model we are able to improve on the rank one recognition rate of the previous state-of-the-art by more than 25% on a challenging dataset of ear images captured from the web (a.k.a. in the wild).},

keywords = {CNN, convolutional neural networks, ear, ear recognition, limited data, model learning},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{emersic2017covariate,

title = {Covariate analysis of descriptor-based ear recognition techniques},

author = {Ziga Emersic and Blaz Meden and Peter Peer and Vitornir Struc},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2019/08/Covariate_Analysis_of_Descriptor_based_Ear_Recognition_Techniques.pdf},

year  = {2017},

date = {2017-01-01},

booktitle = {2017 international conference and workshop on bioinspired intelligence (IWOBI)},

pages = {1--9},

organization = {IEEE},

abstract = {Dense descriptor-based feature extraction techniques represent a popular choice for implementing biometric ear recognition system and are in general considered to be the current state-of-the-art in this area. In this paper, we study the impact of various factors (i.e., head rotation, presence of occlusions, gender and ethnicity) on the performance of 8 state-of-the-art descriptor-based ear recognition techniques. Our goal is to pinpoint weak points of the existing technology and identify open problems worth exploring in the future. We conduct our covariate analysis through identification experiments on the challenging AWE (Annotated Web Ears) dataset and report our findings. The results of our study show that high degrees of head movement and presence of accessories significantly impact the identification performance, whereas mild degrees of the listed factors and other covariates such as gender and ethnicity impact the identification performance only to a limited extent.},

keywords = {AWE, covariate analysis, descriptors, ear, performance evaluation},

pubstate = {published},

tppubtype = {inproceedings}

}