Objave

@inproceedings{MarijaTomato2023,

title = {TomatoDIFF: On–plant Tomato Segmentation with Denoising Diffusion Models},

author = {Marija Ivanovska and Vitomir Štruc and Janez Perš },

url = {https://arxiv.org/pdf/2307.01064.pdf

https://ieeexplore.ieee.org/document/10215774},

doi = {10.23919/MVA57639.2023.10215774},

year  = {2023},

date = {2023-07-23},

urldate = {2023-07-23},

booktitle = {18th International Conference on Machine Vision and Applications (MVA 2023)},

pages = {1-6},

abstract = {Artificial intelligence applications enable farmers to optimize crop growth and production while reducing costs and environmental impact. Computer vision-based algorithms in particular, are commonly used for fruit segmentation, enabling in-depth analysis of the harvest quality and accurate yield estimation. In this paper, we propose TomatoDIFF, a novel diffusion-based model for semantic segmentation of on-plant tomatoes. When evaluated against other competitive methods, our model demonstrates

state-of-the-art (SOTA) performance, even in challenging environments with highly occluded fruits. Additionally, we introduce Tomatopia, a new, large and challenging dataset of greenhouse tomatoes. The dataset comprises high-resolution RGB-D images and pixel-level annotations of the fruits. The source code of TomatoDIFF and Tomatopia are available at https://github. com/MIvanovska/TomatoDIFF},

keywords = {agriculture, dataset, deep learning, diffusion, plan segmentation, plant monitoring, robotics, segmentation, tomato dataset},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{TomasevicIJCBBiOcular,

title = {BiOcularGAN: Bimodal Synthesis and Annotation of Ocular Images},

author = {Darian Tomašević and Peter Peer and Vitomir Štruc },

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2022/12/BiModal_StyleGAN.pdf

https://arxiv.org/pdf/2205.01536.pdf},

year  = {2022},

date = {2022-10-20},

urldate = {2022-10-20},

booktitle = {IEEE/IAPR International Joint Conference on Biometrics (IJCB 2022) },

pages = {1-10},

abstract = {Current state-of-the-art segmentation techniques for ocular images are critically dependent on large-scale annotated datasets, which are labor-intensive to gather and often raise privacy concerns. In this paper, we present a novel framework, called BiOcularGAN, capable of generating synthetic large-scale datasets of photorealistic (visible light and near-infrared) ocular images, together with corresponding segmentation labels to address these issues. At its core, the framework relies on a novel Dual-Branch StyleGAN2 (DB-StyleGAN2) model that facilitates bimodal image generation, and a Semantic Mask Generator (SMG) component that produces semantic annotations by exploiting latent features of the DB-StyleGAN2 model. We evaluate BiOcularGAN through extensive experiments across five diverse ocular datasets and analyze the effects of bimodal data generation on image quality and the produced annotations. Our experimental results show that BiOcularGAN is able to produce high-quality matching bimodal images and annotations (with minimal manual intervention) that can be used to train highly competitive (deep) segmentation models (in a privacy aware-manner) that perform well across multiple real-world datasets. The source code for the BiOcularGAN framework is publicly available at: https://github.com/dariant/BiOcularGAN.},

keywords = {biometrics, CNN, data synthesis, deep learning, ocular, segmentation, StyleGAN, synthetic data},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{JulijanJugBody,

title = {Body Segmentation Using Multi-task Learning},

author = {Julijan Jug and Ajda Lampe and Vitomir Štruc and Peter Peer},

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

doi = {10.1109/ICAIIC54071.2022.9722662},

isbn = {978-1-6654-5818-4},

year  = {2022},

date = {2022-01-20},

urldate = {2022-01-20},

booktitle = {International Conference on Artificial Intelligence in Information and Communication (ICAIIC)},

publisher = {IEEE},

abstract = {Body segmentation is an important step in many computer vision problems involving human images and one of the key components that affects the performance of all downstream tasks.  Several prior works have approached this problem using a multi-task model that exploits correlations between different tasks to improve segmentation performance.  Based on the success of such solutions, we present in this paper a novel multi-task model for human segmentation/parsing that involves three tasks, i.e., (i) keypoint-based skeleton estimation, (ii) dense pose prediction, and (iii) human-body segmentation. The main idea behind the proposed Segmentation--Pose--DensePose model (or SPD for short) is to learn a  better segmentation model by sharing knowledge across different, yet related tasks. SPD is based on a shared deep neural network backbone that branches off into three task-specific model heads and is learned using a multi-task optimization objective. The performance of the  model is analysed through rigorous experiments on the  LIP and ATR datasets and in comparison to a recent (state-of-the-art) multi-task body-segmentation model. Comprehensive ablation studies are also presented. Our experimental results show that the proposed multi-task (segmentation) model is highly competitive and that the introduction of additional tasks contributes towards a higher overall segmentation performance. },

keywords = {body segmentation, cn, CNN, computer vision, deep beauty, deep learning, multi-task learning, segmentation, virtual try-on},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{NIR_IJCB2021,

title = {NIR Iris Challenge Evaluation in Non-cooperative Environments: Segmentation and Localization},

author = {Caiyong Wang and Yunlong Wang and Kunbo Zhang and Jawad Muhammad and Tianhao Lu and Qi Zhang and Qichuan Tian and Zhaofeng He and Zhenan Sun and Yiwen Zhang and Tianbao Liu and Wei Yang and Dongliang Wu and Yingfeng Liu and Ruiye Zhou and Huihai Wu and Hao Zhang and Junbao Wang and Jiayi Wang and Wantong Xiong and Xueyu Shi and Shao Zeng and Peihua Li and Haodong Sun and Jing Wang and Jiale Zhang and Qi Wang and Huijie Wu and Xinhui Zhang and Haiqing Li and Yu Chen and Liang Chen and Menghan Zhang and Ye Sun and Zhiyong Zhou and Fadi Boutros and Naser Damer and Arjan Kuijper and Juan Tapia and Andres Valenzuela and Christoph Busch and Gourav Gupta and Kiran Raja and Xi Wu and Xiaojie Li and Jingfu Yang and Hongyan Jing and Xin Wang and Bin Kong and Youbing Yin and Qi Song and Siwei Lyu and Shu Hu and Leon Premk and Matej Vitek and Vitomir Štruc and Peter Peer and Jalil Nourmohammadi Khiarak and Farhang Jaryani and Samaneh Salehi Nasab and Seyed Naeim Moafinejad and Yasin Amini and Morteza Noshad},

url = {https://ieeexplore.ieee.org/iel7/9484326/9484328/09484336.pdf?casa_token=FOKx4ltO-hYAAAAA:dCkNHfumDzPGkAipRdbppNWpzAiUYUrJL6OrAjNmimTxUA0Vmx311-3-J3ej7YQc_zONxEO-XKo},

doi = {10.1109/IJCB52358.2021.9484336},

year  = {2021},

date = {2021-08-01},

booktitle = {Proceedings of the IEEE International Joint Conference on Biometrics (IJCB 2021)},

abstract = {For iris recognition in non-cooperative environments, iris segmentation has been regarded as the first most important challenge still open to the biometric community, affecting all downstream tasks from normalization to recognition. In recent years, deep learning technologies have gained significant popularity among various computer vision tasks and also been introduced in iris biometrics, especially iris segmentation. To investigate recent developments and attract more interest of researchers in the iris segmentation method, we organized the 2021 NIR Iris Challenge Evaluation in Non-cooperative Environments: Segmentation and Localization (NIR-ISL 2021) at the 2021 International Joint Conference on Biometrics (IJCB 2021). The challenge was used as a public platform to assess the performance of iris segmentation and localization methods on Asian and African NIR iris images captured in non-cooperative environments. The three best-performing entries achieved solid and satisfactory iris segmentation and localization results in most cases, and their code and models have been made publicly available for reproducibility research.},

keywords = {biometrics, competition, iris, segmentation},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{SSBC2020,

title = {SSBC 2020: Sclera Segmentation Benchmarking Competition in the Mobile Environment},

author = {M. Vitek and A. Das and Y. Pourcenoux and A. Missler and C. Paumier and S. Das and I. De Ghosh and D. R. Lucio and L. A. Zanlorensi Jr. and D. Menotti and F. Boutros and N. Damer and J. H. Grebe and A. Kuijper and J. Hu and Y. He and C. Wang and H. Liu and Y. Wang and Z. Sun and D. Osorio-Roig and C. Rathgeb and C. Busch and J. Tapia and A.~Valenzuela and G. Zampoukis and L. Tsochatzidis and I. Pratikakis and S. Nathan and R. Suganya and V. Mehta and A. Dhall and K. Raja and G. Gupta and J. N. Khiarak and M. Akbari-Shahper and F. Jaryani and M. Asgari-Chenaghlu and R. Vyas and S. Dakshit and S. Dakshit and P. Peer and U. Pal and V. Štruc},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2020/11/IJCB_SSBC_2020.pdf},

year  = {2020},

date = {2020-09-28},

booktitle = {International Joint Conference on Biometrics (IJCB 2020)},

pages = {1--10},

abstract = {The paper presents a summary of the 2020 Sclera Segmentation Benchmarking Competition (SSBC), the 7th in the series of group benchmarking efforts centred around the problem of sclera segmentation. Different from previous editions, the goal of SSBC 2020 was to evaluate the performance of sclera-segmentation models on images captured with mobile devices. The competition was used as a platform to assess the sensitivity of existing models to i) differences in mobile devices used for image capture and ii) changes in the ambient acquisition conditions. 26 research groups registered for SSBC 2020, out of which 13 took part in the final round and submitted a total of 16 segmentation models for scoring. These included a wide variety of deep-learning solutions as well as one approach based on standard image processing techniques. Experiments were conducted with three recent datasets. Most of the segmentation models achieved relatively consistent  performance across images captured with different mobile devices (with slight differences across devices), but struggled most with  low-quality images captured in challenging ambient conditions, i.e., in an indoor environment and with poor lighting. },

keywords = {biometrics, competition IJCB, ocular, sclera, segmentation, SSBC},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{sircelj2020sqcnn,

title = {Segmentation and Recovery of Superquadric Models using Convolutional Neural Networks},

author = {Jaka Šircelj and Tim Oblak and Klemen Grm and Uroš Petković and Aleš Jaklič and Peter Peer and Vitomir Štruc and Franc Solina},

url = {https://lmi.fe.uni-lj.si/en/sircelj2020cvww/

https://arxiv.org/abs/2001.10504},

year  = {2020},

date = {2020-02-03},

booktitle = {25th Computer Vision Winter Workshop (CVWW 2020)},

abstract = {In this paper we address the problem of representing 3D visual data with parameterized volumetric shape primitives. Specifically, we present a (two-stage) approach built around convolutional neural networks (CNNs) capable of segmenting complex depth scenes into the simpler geometric structures that can be represented with superquadric models. In the first stage, our approach uses a Mask RCNN model to identify superquadric-like structures in depth scenes and then fits superquadric models to the segmented structures using a specially designed CNN regressor. Using our approach we are able to describe complex structures with a small number of interpretable parameters. We evaluated the proposed approach on synthetic as well as real-world depth data and show that our solution does not only result in competitive performance in comparison to the state-of-the-art, but is able to decompose scenes into a number of superquadric models at a fraction of the time required by competing approaches. We make all data and models used in the paper available from https://lmi.fe.uni-lj.si/en/research/resources/sq-seg.},

keywords = {CNN, convolutional neural networks, segmentation, superquadrics, volumetric data},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{lozej2019influence,

title = {Influence of segmentation on deep iris recognition performance},

author = {Juš Lozej and Dejan Štepec and Vitomir Štruc and Peter Peer},

url = {https://arxiv.org/pdf/1901.10431.pdf},

year  = {2019},

date = {2019-03-01},

booktitle = {7th IAPR/IEEE International Workshop on Biometrics and Forensics (IWBF 2019)},

journal = {arXiv preprint arXiv:1901.10431},

abstract = {Despite the rise of deep learning in numerous areas of computer vision and image processing, iris recognition has not benefited considerably from these trends so far. Most of the existing research on deep iris recognition is focused on new models for generating discriminative and robust iris representations and relies on methodologies akin to traditional iris recognition pipelines. Hence, the proposed models do not approach iris recognition in an end-to-end manner, but rather use standard heuristic iris segmentation (and unwrapping) techniques to produce normalized inputs for the deep learning models. However, because deep learning is able to model very complex data distributions and nonlinear data changes, an obvious question arises. How important is the use of traditional segmentation methods in a deep learning setting? To answer this question, we present in this paper an empirical analysis of the impact of iris segmentation on the performance of deep learning models using a simple two stage pipeline consisting of a segmentation and a recognition step. We evaluate how the accuracy of segmentation influences recognition performance but also examine if segmentation is needed at all. We use the CASIA Thousand and SBVPI datasets for the experiments and report several interesting findings.},

keywords = {biometrics, iris, ocular, segmentation},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{rot2018deep,

title = {Deep multi-class eye segmentation for ocular biometrics},

author = {Peter Rot and Žiga Emeršič and Vitomir Struc and Peter Peer},

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

year  = {2018},

date = {2018-07-01},

booktitle = {2018 IEEE International Work Conference on Bioinspired Intelligence (IWOBI)},

pages = {1--8},

organization = {IEEE},

abstract = {Segmentation techniques for ocular biometrics typically focus on finding a single eye region in the input image at the time. Only limited work has been done on multi-class eye segmentation despite a number of obvious advantages. In this paper we address this gap and present a deep multi-class eye segmentation model build around the SegNet architecture. We train the model on a small dataset (of 120 samples) of eye images and observe it to generalize well to unseen images and to ensure highly accurate segmentation results. We evaluate the model on the Multi-Angle Sclera Database (MASD) dataset and describe comprehensive experiments focusing on: i) segmentation performance, ii) error analysis, iii) the sensitivity of the model to changes in view direction, and iv) comparisons with competing single-class techniques. Our results show that the proposed model is viable solution for multi-class eye segmentation suitable for recognition (multi-biometric) pipelines based on ocular characteristics.},

keywords = {biometrics, eye, ocular, sclera, segmentation},

pubstate = {published},

tppubtype = {inproceedings}

}