Objave

@inproceedings{UERC2026,

title = {The Unconstrained Ear Recognition Challenge 2026: Size Matters - Ear Biometrics on Edge},

author = {D. Sušanj and J. Jin and M. Tokumasu and T. Ohki and A. Kamboj and A. Rai and S. Aggarwal and S. Ahluwalia and M. Chipade and A. Sharma and D. Pinčić and M. Banov and K. Lenac and K. Shigematsu and K. Inoue and A. Shin and H. Shirono and A. Hazra and T. Batabyal and S. Pal and D. Freire-Obregón and G. Gupta and A. Gupta and D. Arun and P. Flynn and J. L. Godoy and D. D. A. Ruiz and J. N. Khiarak and F. N. Khiarak and T.A. Saeed and L.D.M.S.S. Teja and D.P. Chowdhury and

K. Griparić and R. Lajić and D. Tomašević and B. Meden and H.K. Ekenel and G. Cámara-Chávez and V. Štruc and P. Peer and Ž. Emeršič},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2026/09/UERC26.pdf},

year  = {2026},

date = {2026-09-04},

urldate = {2026-09-04},

booktitle = {Proceedings of the IEEE/IAPR International Joint Conference on Biometrics (IJCB)},

pages = {1--10},

abstract = {The 2026 Unconstrained Ear Recognition Challenge (UERC 2026), a benchmarking competition focused on lightweight and efficient ear recognition from images captured in uncontrolled environments. Building on the previous editions of the UERC series, the 2026 challenge introduced a novel evaluation paradigm that jointly assesses recognition accuracy and computational efficiency, with the goal of promoting the development of compact ear recognition models suitable for deployment on resource-constrained and edge platforms. The competition was organized into two tracks: Track 1: Lightweight Model Design, which focused on balancing recognition performance with model efficiency through a composite evaluation criterion combining verification accuracy, parameter count, and model size, and Track 2: Edge Deployment which assessed recognition accuracy together with end-to-end inference time on a standardized Raspberry Pi 4 platform. A total of 11 research groups participated in Track 1 and 8 groups competed in Track 2, submitting solutions spanning a wide range of architectures including lightweight convolutional networks, vision transformers, ensemble-distillation pipelines, and ONNX-accelerated models.

The results demonstrate that carefully designed compact architectures, such as knowledge-distilled MobileNetV4 and INT8-quantized TinyViT networks, can achieve competitive verification performance while drastically reducing parameter counts and inference time.

The competition's starter kit, baseline code, and dataset are publicly available at http://uerc.fri.uni-lj.si/.},

keywords = {competition, competition IJCB, ear, ear biometrics, ear recognition},

pubstate = {published},

tppubtype = {inproceedings}

}

@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}

}