Florian Kirchbuchner

@Https:

Smart Living & Biometric Technologies
Fraunhofer Institute for Computer Graphics Research IGD

Florian Kirchbuchner


                        Download Compact PDF  
https://researchid.co/floriankirchbuchner
94

Scopus Publications

4223

Scholar Citations

38

Scholar h-index

73

Scholar i10-index

Scopus Publications

  • Ubiquitous multi-occupant detection in smart environments
    Daniel Fährmann, Fadi Boutros, Philipp Kubon, Florian Kirchbuchner, Arjan Kuijper, et al.
    Neural Computing and Applications, 2024
    Recent advancements in ubiquitous computing have emphasized the need for privacy-preserving occupancy detection in smart environments to enhance security. This work presents a novel occupancy detection solution utilizing privacy-aware sensing technologies. The solution analyzes time-series data to detect not only occupancy as a binary problem, but also determines whether one or multiple individuals are present in an indoor environment. On three real-world datasets, our models outperformed various state-of-the-art algorithms, achieving F1-scores up to 94.91% in single-occupancy detection and a macro F1-score of 91.55% in multi-occupancy detection. This makes our approach a promising solution for improving security in smart environments.
  • Artificial intelligence in everyday clinical and nursing care
    Medizintechnik Cologne, 2024
  • VeinXam: A Low-Cost Deep Veins Function Assessment
    Vincent Abt, Julian von Wilmsdorff, Silvia Faquiri, Florian Kirchbuchner
    Ubicomp Iswc 2023 Adjunct Adjunct Proceedings of the 2023 ACM International Joint Conference on Pervasive and Ubiquitous Computing and the 2023 ACM International Symposium on Wearable Computing, 2023
    A venous insufficiency, to which the deep veins of the lower human extremities are particularly susceptible, can lead to serious diseases, such as a deep vein thrombosis (DVT) with subsequent risks of severe implications, e.g. pulmonary embolism or a post-thrombotic syndrome (PTS) [6]. The current standard procedure to diagnose venous insufficiency is performed exclusively in medical offices and hospitals in the form of in-patient treatments with special medical equipment. This hurdle for the patient, combined with the often diffuse symptoms of venous insufficiency [7], may lead to a late discovery of diseases such as DVTs and increases the risk of secondary diseases as well as treatment costs [3]. To address these issues, we propose a novel method for continuous monitoring of the current venous function by adapting the Light Reflection Rheography (LLR) and using low-cost wearable sensor technology and a smartphone app, aiming to deliver critical early stage information about pathological changes of the blood flow in the lower limbs.
  • Pixel-Level Face Image Quality Assessment for Explainable Face Recognition
    Philipp Terhörst, Marco Huber, Naser Damer, Florian Kirchbuchner, Kiran Raja, et al.
    IEEE Transactions on Biometrics Behavior and Identity Science, 2023
    An essential factor to achieve high performance in face recognition systems is the quality of its samples. Since these systems are involved in daily life there is a strong need of making face recognition processes understandable for humans. In this work, we introduce the concept of pixel-level face image quality that determines the utility of pixels in a face image for recognition. We propose a training-free approach to assess the pixel-level qualities of a face image given an arbitrary face recognition network. To achieve this, a model-specific quality value of the input image is estimated and used to build a sample-specific quality regression model. Based on this model, quality-based gradients are back-propagated and converted into pixel-level quality estimates. In the experiments, we qualitatively and quantitatively investigated the meaningfulness of our proposed pixel-level qualities based on real and artificial disturbances and by comparing the explanation maps on faces incompliant with the ICAO standards. In all scenarios, the results demonstrate that the proposed solution produces meaningful pixel-level qualities enhancing the interpretability of the complete face image quality. The code is publicly available
  • Uncertainty-aware Comparison Scores for Face Recognition
    Marco Huber, Philipp Terhörst, Florian Kirchbuchner, Arjan Kuijper, Naser Damer
    2023 11th International Workshop on Biometrics and Forensics Iwbf 2023, 2023
    Estimating and understanding uncertainty in face recognition systems is receiving increasing attention as face recognition systems spread worldwide and process privacy and security-related data. In this work, we investigate how such uncertainties can be further utilized to increase the accuracy and therefore the trust of automatic face recognition systems. We propose to use the uncertainties of extracted face features to compute a new uncertainty-aware comparison score (UACS). This score takes into account the estimated uncertainty during the calculation of the comparison score, leading to a reduction in verification errors. To achieve this, we model the comparison score and its uncertainty as a probability distribution and measure its distance to a distribution of an ideal genuine comparison. In extended experiments with three face recognition models and on six benchmarks, we investigated the impact of our approach and demonstrated its benefits in enhancing the verification performance and the genuine-imposter comparison scores separability.
  • QMagFace: Simple and Accurate Quality-Aware Face Recognition
    Philipp Terhorst, Malte Ihlefeld, Marco Huber, Naser Damer, Florian Kirchbuchner, et al.
    Proceedings 2023 IEEE Winter Conference on Applications of Computer Vision Wacv 2023, 2023
    In this work, we propose QMagFace, a simple and effective face recognition solution (QMagFace) that combines a quality-aware comparison score with a recognition model based on a magnitude-aware angular margin loss. The proposed approach includes model-specific face image qualities in the comparison process to enhance the recognition performance under unconstrained circumstances. Exploiting the linearity between the qualities and their comparison scores induced by the utilized loss, our quality-aware comparison function is simple and highly generalizable. The experiments conducted on several face recognition databases and benchmarks demonstrate that the introduced quality-awareness leads to consistent improvements in the recognition performance. Moreover, the proposed QMagFace approach performs especially well under challenging circumstances, such as cross-pose, cross-age, or cross-quality. Consequently, it leads to state-of-the-art performances on several face recognition benchmarks, such as 98.50% on AgeDB, 83.95% on XQLFQ, and 98.74% on CFP-FP. The code for QMagFace is publicly available1.
  • Masked face recognition: Human versus machine
    Naser Damer, Fadi Boutros, Marius Süßmilch, Meiling Fang, Florian Kirchbuchner, et al.
    Iet Biometrics, 2022
  • Self-restrained triplet loss for accurate masked face recognition
    Fadi Boutros, Naser Damer, Florian Kirchbuchner, Arjan Kuijper
    Pattern Recognition, 2022
    Using the face as a biometric identity trait is motivated by the contactless nature of the capture process and the high accuracy of the recognition algorithms. After the current COVID-19 pandemic, wearing a face mask has been imposed in public places to keep the pandemic under control. However, face occlusion due to wearing a mask presents an emerging challenge for face recognition systems. In this paper, we present a solution to improve masked face recognition performance. Specifically, we propose the Embedding Unmasking Model (EUM) operated on top of existing face recognition models. We also propose a novel loss function, the Self-restrained Triplet (SRT), which enabled the EUM to produce embeddings similar to these of unmasked faces of the same identities. The achieved evaluation results on three face recognition models, two real masked datasets, and two synthetically generated masked face datasets proved that our proposed approach significantly improves the performance in most experimental settings.
  • Lightweight Long Short-Term Memory Variational Auto-Encoder for Multivariate Time Series Anomaly Detection in Industrial Control Systems
    Daniel Fährmann, Naser Damer, Florian Kirchbuchner, Arjan Kuijper
    Sensors, 2022
    Heterogeneous cyberattacks against industrial control systems (ICSs) have had a strong impact on the physical world in recent decades. Connecting devices to the internet enables new attack surfaces for attackers. The intrusion of ICSs, such as the manipulation of industrial sensory or actuator data, can be the cause for anomalous ICS behaviors. This poses a threat to the infrastructure that is critical for the operation of a modern city. Nowadays, the best techniques for detecting anomalies in ICSs are based on machine learning and, more recently, deep learning. Cybersecurity in ICSs is still an emerging field, and industrial datasets that can be used to develop anomaly detection techniques are rare. In this paper, we propose an unsupervised deep learning methodology for anomaly detection in ICSs, specifically, a lightweight long short-term memory variational auto-encoder (LW-LSTM-VAE) architecture. We successfully demonstrate our solution under two ICS applications, namely, water purification and water distribution plants. Our proposed method proves to be efficient in detecting anomalies in these applications and improves upon reconstruction-based anomaly detection methods presented in previous work. For example, we successfully detected 82.16% of the anomalies in the scenario of the widely used Secure Water Treatment (SWaT) benchmark. The deep learning architecture we propose has the added advantage of being extremely lightweight.
  • Real masks and spoof faces: On the masked face presentation attack detection
    Meiling Fang, Naser Damer, Florian Kirchbuchner, Arjan Kuijper
    Pattern Recognition, 2022
    Face masks have become one of the main methods for reducing the transmission of COVID-19. This makes face recognition (FR) a challenging task because masks hide several discriminative features of faces. Moreover, face presentation attack detection (PAD) is crucial to ensure the security of FR systems. In contrast to the growing number of masked FR studies, the impact of face masked attacks on PAD has not been explored. Therefore, we present novel attacks with real face masks placed on presentations and attacks with subjects wearing masks to reflect the current real-world situation. Furthermore, this study investigates the effect of masked attacks on PAD performance by using seven state-of-the-art PAD algorithms under different experimental settings. We also evaluate the vulnerability of FR systems to masked attacks. The experiments show that real masked attacks pose a serious threat to the operation and security of FR systems.
  • Template-Driven Knowledge Distillation for Compact and Accurate Periocular Biometrics Deep-Learning Models
    Fadi Boutros, Naser Damer, Kiran Raja, Florian Kirchbuchner, Arjan Kuijper
    Sensors, 2022
  • A Comprehensive Study on Face Recognition Biases beyond Demographics
    Philipp Terhorst, Jan Niklas Kolf, Marco Huber, Florian Kirchbuchner, Naser Damer, et al.
    IEEE Transactions on Technology and Society, 2022
  • Acquisition of EFS and Capacitive Measurement Data on Low-Power and Connected IoT Devices
    Julian von Wilmsdorff, Malte Lenhart, Florian Kirchbuchner, Arjan Kuijper
    Communications in Computer and Information Science, 2022
  • Learnable Multi-level Frequency Decomposition and Hierarchical Attention Mechanism for Generalized Face Presentation Attack Detection
    Meiling Fang, Naser Damer, Florian Kirchbuchner, Arjan Kuijper
    Proceedings 2022 IEEE Cvf Winter Conference on Applications of Computer Vision Wacv 2022, 2022
  • Lightweight Periocular Recognition through Low-bit Quantization
    Jan Niklas Kolf, Fadi Boutros, Florian Kirchbuchner, Naser Damer
    2022 IEEE International Joint Conference on Biometrics Ijcb 2022, 2022
  • ElasticFace: Elastic Margin Loss for Deep Face Recognition
    F. Boutros, N. Damer, Florian Kirchbuchner, Arjan Kuijper
    IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, 2022
  • Verification of Sitter Identity Across Historical Portrait Paintings by Confidence-aware Face Recognition
    Marco Huber, Philipp Terhorst, Anh Thi Luu, Florian Kirchbuchner, Naser Damer
    Proceedings International Conference on Pattern Recognition, 2022
  • The overlapping effect and fusion protocols of data augmentation techniques in iris PAD
    Meiling Fang, Naser Damer, Fadi Boutros, Florian Kirchbuchner, Arjan Kuijper
    Machine Vision and Applications, 2022
  • Stating Comparison Score Uncertainty and Verification Decision Confidence Towards Transparent Face Recognition
    Bmvc 2022 33rd British Machine Vision Conference Proceedings, 2022
  • On Evaluating Pixel-Level Face Image Quality Assessment
    European Signal Processing Conference, 2022
  • Double Deep Q-Learning With Prioritized Experience Replay for Anomaly Detection in Smart Environments
    Daniel Fahrmann, Nils Jorek, Naser Damer, Florian Kirchbuchner, Arjan Kuijper
    IEEE Access, 2022
  • PocketNet: Extreme Lightweight Face Recognition Network Using Neural Architecture Search and Multistep Knowledge Distillation
    Fadi Boutros, Patrick Siebke, Marcel Klemt, Naser Damer, Florian Kirchbuchner, et al.
    IEEE Access, 2022
  • Low-resolution Iris Recognition via Knowledge Transfer
    Fadi Boutros, Olga Kaehm, Meiling Fang, Florian Kirchbuchner, Naser Damer, et al.
    Biosig 2022 Proceedings of the 21st International Conference of the Biometrics Special Interest Group, 2022
  • On the (Limited) Generalization of MasterFace Attacks and Its Relation to the Capacity of Face Representations
    Philipp Terhorst, Florian Bierbaum, Marco Huber, Naser Damer, Florian Kirchbuchner, et al.
    2022 IEEE International Joint Conference on Biometrics Ijcb 2022, 2022
  • On Soft-Biometric Information Stored in Biometric Face Embeddings
    Philipp Terhorst, Daniel Fahrmann, Naser Damer, Florian Kirchbuchner, Arjan Kuijper
    IEEE Transactions on Biometrics Behavior and Identity Science, 2021

RECENT SCHOLAR PUBLICATIONS

  • Erkennung von Mikrobewegungen zur Dekubitusprävention mittels KI-gestützter Sensorsysteme
    S Staab, F Tajja, F Kirchbuchner
    2025
    Citations: 1
  • Towards Mobile Deep Venous Function Assessment: An Algorithmic Approach
    V Abt, S Staab, F Kirchbuchner, A Kuijper
    Intelligent Environments 2025: Combined Workshop Proceedings, 26-35 , 2025
    2025
  • Ubiquitous multi-occupant detection in smart environments
    D Fährmann, F Boutros, P Kubon, F Kirchbuchner, A Kuijper, N Damer
    Neural Computing and Applications 36 (6), 2941-2960 , 2024
    2024
    Citations: 9
  • VeinXam: A low-cost deep veins function assessment
    V Abt, J von Wilmsdorff, S Faquiri, F Kirchbuchner
    Adjunct Proceedings of the 2023 ACM International Joint Conference on … , 2023
    2023
    Citations: 1
  • Uncertainty-aware comparison scores for face recognition
    M Huber, P Terhörst, F Kirchbuchner, A Kuijper, N Damer
    2023 11th International Workshop on Biometrics and Forensics (IWBF), 1-6 , 2023
    2023
    Citations: 4
  • Pixel-level face image quality assessment for explainable face recognition
    P Terhörst, M Huber, N Damer, F Kirchbuchner, K Raja, A Kuijper
    IEEE Transactions on Biometrics, Behavior, and Identity Science 5 (2), 288-297 , 2023
    2023
    Citations: 49
  • Qmagface: Simple and accurate quality-aware face recognition
    P Terhörst, M Ihlefeld, M Huber, N Damer, F Kirchbuchner, K Raja, ...
    Proceedings of the IEEE/CVF Winter Conference on Applications of Computer … , 2023
    2023
    Citations: 93
  • Stating comparison score uncertainty and verification decision confidence towards transparent face recognition
    M Huber, P Terhörst, F Kirchbuchner, N Damer, A Kuijper
    arXiv preprint arXiv:2210.10354 , 2022
    2022
    Citations: 20
  • Lightweight periocular recognition through low-bit quantization
    JN Kolf, F Boutros, F Kirchbuchner, N Damer
    2022 IEEE International Joint Conference on Biometrics (IJCB), 1-12 , 2022
    2022
    Citations: 11
  • On the (limited) generalization of masterface attacks and its relation to the capacity of face representations
    P Terhörst, F Bierbaum, M Huber, N Damer, F Kirchbuchner, K Raja, ...
    2022 IEEE International Joint Conference on Biometrics (IJCB), 1-9 , 2022
    2022
    Citations: 15
  • Low-resolution iris recognition via knowledge transfer
    F Boutros, O Kaehm, M Fang, F Kirchbuchner, N Damer, A Kuijper
    2022 International Conference of the Biometrics Special Interest Group … , 2022
    2022
    Citations: 13
  • Masked face recognition: Human versus machine
    N Damer, F Boutros, M Süßmilch, M Fang, F Kirchbuchner, A Kuijper
    IET biometrics 11 (5), 512-528 , 2022
    2022
    Citations: 14
  • On evaluating pixel-level face image quality assessment
    M Huber, P Terhöst, F Kirchbuchner, N Damer, A Kuijper
    2022 30th European Signal Processing Conference (EUSIPCO), 1052-1056 , 2022
    2022
    Citations: 8
  • Verification of sitter identity across historical portrait paintings by confidence-aware face recognition
    M Huber, P Terhörst, AT Luu, F Kirchbuchner, N Damer
    2022 26th International Conference on Pattern Recognition (ICPR), 938-944 , 2022
    2022
    Citations: 10
  • Double deep q-learning with prioritized experience replay for anomaly detection in smart environments
    D Fährmann, N Jorek, N Damer, F Kirchbuchner, A Kuijper
    IEEE access 10, 60836-60848 , 2022
    2022
    Citations: 45
  • Pocketnet: Extreme lightweight face recognition network using neural architecture search and multistep knowledge distillation
    F Boutros, P Siebke, M Klemt, N Damer, F Kirchbuchner, A Kuijper
    IEEE access 10, 46823-46833 , 2022
    2022
    Citations: 109
  • Lightweight long short-term memory variational auto-encoder for multivariate time series anomaly detection in industrial control systems
    D Fährmann, N Damer, F Kirchbuchner, A Kuijper
    Sensors 22 (8), 2886 , 2022
    2022
    Citations: 79
  • Self-restrained triplet loss for accurate masked face recognition
    F Boutros, N Damer, F Kirchbuchner, A Kuijper
    Pattern Recognition 124, 108473 , 2022
    2022
    Citations: 180
  • Template-driven knowledge distillation for compact and accurate periocular biometrics deep-learning models
    F Boutros, N Damer, K Raja, F Kirchbuchner, A Kuijper
    Sensors 22 (5), 1921 , 2022
    2022
    Citations: 22
  • Real masks and spoof faces: On the masked face presentation attack detection
    M Fang, N Damer, F Kirchbuchner, A Kuijper
    Pattern Recognition 123, 108398 , 2022
    2022
    Citations: 66

MOST CITED SCHOLAR PUBLICATIONS

  • Elasticface: Elastic margin loss for deep face recognition
    F Boutros, N Damer, F Kirchbuchner, A Kuijper
    Proceedings of the IEEE/CVF conference on computer vision and pattern … , 2022
    2022
    Citations: 414
  • SER-FIQ: Unsupervised estimation of face image quality based on stochastic embedding robustness
    P Terhorst, JN Kolf, N Damer, F Kirchbuchner, A Kuijper
    Proceedings of the IEEE/CVF conference on computer vision and pattern … , 2020
    2020
    Citations: 311
  • Sensing technology for human activity recognition: A comprehensive survey
    B Fu, N Damer, F Kirchbuchner, A Kuijper
    Ieee Access 8, 83791-83820 , 2020
    2020
    Citations: 227
  • A comprehensive study on face recognition biases beyond demographics
    P Terhörst, JN Kolf, M Huber, F Kirchbuchner, N Damer, AM Moreno, ...
    IEEE Transactions on Technology and Society 3 (1), 16-30 , 2021
    2021
    Citations: 197
  • Self-restrained triplet loss for accurate masked face recognition
    F Boutros, N Damer, F Kirchbuchner, A Kuijper
    Pattern Recognition 124, 108473 , 2022
    2022
    Citations: 180
  • The effect of wearing a mask on face recognition performance: an exploratory study
    N Damer, JH Grebe, C Chen, F Boutros, F Kirchbuchner, A Kuijper
    2020 International Conference of the Biometrics Special Interest Group … , 2020
    2020
    Citations: 146
  • Pocketnet: Extreme lightweight face recognition network using neural architecture search and multistep knowledge distillation
    F Boutros, P Siebke, M Klemt, N Damer, F Kirchbuchner, A Kuijper
    IEEE access 10, 46823-46833 , 2022
    2022
    Citations: 109
  • Mixfacenets: Extremely efficient face recognition networks
    F Boutros, N Damer, M Fang, F Kirchbuchner, A Kuijper
    2021 IEEE International Joint Conference on Biometrics (IJCB), 1-8 , 2021
    2021
    Citations: 101
  • Qmagface: Simple and accurate quality-aware face recognition
    P Terhörst, M Ihlefeld, M Huber, N Damer, F Kirchbuchner, K Raja, ...
    Proceedings of the IEEE/CVF Winter Conference on Applications of Computer … , 2023
    2023
    Citations: 93
  • Post-comparison mitigation of demographic bias in face recognition using fair score normalization
    P Terhörst, JN Kolf, N Damer, F Kirchbuchner, A Kuijper
    Pattern Recognition Letters 140, 332-338 , 2020
    2020
    Citations: 86
  • Ambient intelligence from senior citizens’ perspectives: Understanding privacy concerns, technology acceptance, and expectations
    F Kirchbuchner, T Grosse-Puppendahl, MR Hastall, M Distler, A Kuijper
    European conference on ambient intelligence, 48-59 , 2015
    2015
    Citations: 85
  • Iris and periocular biometrics for head mounted displays: Segmentation, recognition, and synthetic data generation
    F Boutros, N Damer, K Raja, R Ramachandra, F Kirchbuchner, A Kuijper
    Image and Vision Computing 104, 104007 , 2020
    2020
    Citations: 82
  • MFR 2021: Masked face recognition competition
    F Boutros, N Damer, JN Kolf, K Raja, F Kirchbuchner, R Ramachandra, ...
    2021 IEEE International joint conference on biometrics (IJCB), 1-10 , 2021
    2021
    Citations: 81
  • Lightweight long short-term memory variational auto-encoder for multivariate time series anomaly detection in industrial control systems
    D Fährmann, N Damer, F Kirchbuchner, A Kuijper
    Sensors 22 (8), 2886 , 2022
    2022
    Citations: 79
  • Learnable multi-level frequency decomposition and hierarchical attention mechanism for generalized face presentation attack detection
    M Fang, N Damer, F Kirchbuchner, A Kuijper
    Proceedings of the IEEE/CVF winter conference on applications of computer … , 2022
    2022
    Citations: 69
  • Maad-face: A massively annotated attribute dataset for face images
    P Terhörst, D Fährmann, JN Kolf, N Damer, F Kirchbuchner, A Kuijper
    IEEE Transactions on Information Forensics and Security 16, 3942-3957 , 2021
    2021
    Citations: 69
  • Real masks and spoof faces: On the masked face presentation attack detection
    M Fang, N Damer, F Kirchbuchner, A Kuijper
    Pattern Recognition 123, 108398 , 2022
    2022
    Citations: 66
  • Pw-mad: Pixel-wise supervision for generalized face morphing attack detection
    N Damer, N Spiller, M Fang, F Boutros, F Kirchbuchner, A Kuijper
    International Symposium on Visual Computing, 291-304 , 2021
    2021
    Citations: 63
  • Face quality estimation and its correlation to demographic and non-demographic bias in face recognition
    P Terhörst, JN Kolf, N Damer, F Kirchbuchner, A Kuijper
    2020 IEEE International Joint Conference on Biometrics (IJCB), 1-11 , 2020
    2020
    Citations: 61
  • Beyond identity: What information is stored in biometric face templates?
    P Terhörst, D Fährmann, N Damer, F Kirchbuchner, A Kuijper
    2020 IEEE international joint conference on biometrics (IJCB), 1-10 , 2020
    2020
    Citations: 59