Ayyoub Ahar
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Ayyoub Ahar has a total of 40 co-authors. Here are the top co-authors by number of shared publications:
- Peter Schelkens
Vrije Universiteit Brussel (VUB)
3 shared publications Weronika Zaperty
3 shared publications- Abdellatif Bey-Temsamani
Flanders Make, Gaston Geenslaan 8, 3001 Heverlee, Belgium
2 shared publications Flanders Make
2 shared publications- Maksymilian Chlipala
Warsaw University of Technology
2 shared publications - Malgorzata Kujawinska
Warsaw University of Technology, Institute of Micromechanics and Photonics
2 shared publications
Latest Publications
- 11 October 2026
- Published by European Powder Metallurgy Association
Sound Of Porosity: Unlocking Local Acoustic Signatures Of Porosity In LPBF Via Low-Cost Sensing And Explainable AI
Conventional in-situ monitoring solutions—such as high-speed cameras, SWIR imaging, and acoustic emission sensors—are costly, data-intensive, and impractical for industrial deployment. In this work, we demonstrate a low-cost, off-the-shelf ultrasonic microphone installed inside the build chamber as a practical alternative for capturing high-resolution acoustic signals during LPBF. Using these signals, we benchmark multiple machine learning architectures for localized porosity prediction. Targets for lack-of-fusion and keyhole porosity are derived from volumetric X-ray Computed Tomography (XCT) analysis and carefully registered to process coordinates, enabling supervised learning at scanline granularity. Beyond performance evaluation, we conduct explainability analysis using feature attribution methods to uncover which acoustic signatures most strongly correlate with defect formation. Results show that acoustic-based models achieve low-latency inference, suitable for in-process monitoring, paving the way for adaptive corrective control strategies. This study establishes a new paradigm for practical, scalable LPBF quality assurance by combining low-cost sensing with interpretable AI.
- 11 October 2026
- Published by European Powder Metallurgy Association
Sound Of Porosity: Unlocking Local Acoustic Signatures Of Porosity In LPBF Via Low-Cost Sensing And Explainable AI
Conventional in-situ monitoring solutions—such as high-speed cameras, SWIR imaging, and acoustic emission sensors—are costly, data-intensive, and impractical for industrial deployment. In this work, we demonstrate a low-cost, off-the-shelf ultrasonic microphone installed inside the build chamber as a practical alternative for capturing high-resolution acoustic signals during LPBF. Using these signals, we benchmark multiple machine learning architectures for localized porosity prediction. Targets for lack-of-fusion and keyhole porosity are derived from volumetric X-ray Computed Tomography (XCT) analysis and carefully registered to process coordinates, enabling supervised learning at scanline granularity. Beyond performance evaluation, we conduct explainability analysis using feature attribution methods to uncover which acoustic signatures most strongly correlate with defect formation. Results show that acoustic-based models achieve low-latency inference, suitable for in-process monitoring, paving the way for adaptive corrective control strategies. This study establishes a new paradigm for practical, scalable LPBF quality assurance by combining low-cost sensing with interpretable AI.
- Open Access
- 30 September 2026
- Published by MDPI AG in Agriengineering
- Vol. 8 (10) , 414
Synthetic Data for Data-Efficient Agricultural Computer Vision: Three Datasets and a Multi-Task Benchmark Across Real and Simulated Domains
The availability of large annotated datasets remains a major bottleneck for deploying computer vision systems in agricultural and agri-food applications, particularly for tasks requiring fine-grained annotations such as defect detection and instance segmentation. Synthetic data generation offers a scalable alternative, but its effectiveness in complex real-world scenarios remains insufficiently understood. In this work, the role of synthetic data is investigated across three representative tasks each posing unique challenges: apple detection in orchard environments, potato–stone classification in industrial sorting, and carrot crack detection for quality inspection. The real and synthetic data, as well as their annotations, are publicly available. The synthetic data is created using a set of tools for fast large-scale procedural scene generation with highly detailed natural assets. For each task, datasets are constructed combining real and synthetically generated images with pixel-level annotations. Training strategies are systematically evaluated using fully real, limited real, synthetic-only, and combined datasets. The results show that synthetic-only training leads to a clear performance gap on real-world data, with mAP50 decreasing from 0.866–0.891 for fully real training to 0.396–0.703 for synthetic-only training across the three use cases. However, combining synthetic data with only 10 real images recovers 75–98% of the gap between training on those 10 real images alone (mAP50 0.194–0.497) and full real training, reaching mAP50 values of 0.723–0.885. These findings highlight the potential of synthetic data for improving data efficiency and provide a reproducible benchmark for future research on sim-to-real transfer in agricultural computer vision.
- 30 September 2026
- Published by MDPI AG in Agriengineering
- Vol. 8 (10) , 414
Open AccessSynthetic Data for Data-Efficient Agricultural Computer Vision: Three Datasets and a Multi-Task Benchmark Across Real and Simulated Domains
The availability of large annotated datasets remains a major bottleneck for deploying computer vision systems in agricultural and agri-food applications, particularly for tasks requiring fine-grained annotations such as defect detection and instance segmentation. Synthetic data generation offers a scalable alternative, but its effectiveness in complex real-world scenarios remains insufficiently understood. In this work, the role of synthetic data is investigated across three representative tasks each posing unique challenges: apple detection in orchard environments, potato–stone classification in industrial sorting, and carrot crack detection for quality inspection. The real and synthetic data, as well as their annotations, are publicly available. The synthetic data is created using a set of tools for fast large-scale procedural scene generation with highly detailed natural assets. For each task, datasets are constructed combining real and synthetically generated images with pixel-level annotations. Training strategies are systematically evaluated using fully real, limited real, synthetic-only, and combined datasets. The results show that synthetic-only training leads to a clear performance gap on real-world data, with mAP50 decreasing from 0.866–0.891 for fully real training to 0.396–0.703 for synthetic-only training across the three use cases. However, combining synthetic data with only 10 real images recovers 75–98% of the gap between training on those 10 real images alone (mAP50 0.194–0.497) and full real training, reaching mAP50 values of 0.723–0.885. These findings highlight the potential of synthetic data for improving data efficiency and provide a reproducible benchmark for future research on sim-to-real transfer in agricultural computer vision.
- 11 September 2025
- Published by European Powder Metallurgy Association
A High-speed Multimodal In-situ Monitoring System For Detecting Porosity And Deformation Defects In The Powder Bed Fusion Of Metallic Parts
Porosity and deformation defects remain critical challenges to consistent, high-quality production of metallic parts using powder bed fusion (PBF). Existing state-of-the-art monitoring systems typically lack the speed required for real-time adjustments and often target only single defect types. To address these limitations, we present a high-speed, multi-modal in-situ monitoring system operating at up to 20 kHz. The system integrates dynamic region-of-interest cameras in both the visible and short-wave infrared ranges with a GPU-optimized, machine learning-based image processing pipeline. By incorporating local print context, the system accurately identifies porosity and deformation defects, enabling rapid corrective actions. Validation on 316L stainless steel samples, deliberately engineered to exhibit these defects, demonstrates Pearson correlation coefficients of 0.9493 for porosity prediction and normalized mean absolute errors of 17% for deformation detection. The results show promise for the system to be effectively used for high-speed, intra-layer closed-loop control, significantly improving the PBF process.
- 11 September 2025
- Published by European Powder Metallurgy Association
A High-speed Multimodal In-situ Monitoring System For Detecting Porosity And Deformation Defects In The Powder Bed Fusion Of Metallic Parts
Porosity and deformation defects remain critical challenges to consistent, high-quality production of metallic parts using powder bed fusion (PBF). Existing state-of-the-art monitoring systems typically lack the speed required for real-time adjustments and often target only single defect types. To address these limitations, we present a high-speed, multi-modal in-situ monitoring system operating at up to 20 kHz. The system integrates dynamic region-of-interest cameras in both the visible and short-wave infrared ranges with a GPU-optimized, machine learning-based image processing pipeline. By incorporating local print context, the system accurately identifies porosity and deformation defects, enabling rapid corrective actions. Validation on 316L stainless steel samples, deliberately engineered to exhibit these defects, demonstrates Pearson correlation coefficients of 0.9493 for porosity prediction and normalized mean absolute errors of 17% for deformation detection. The results show promise for the system to be effectively used for high-speed, intra-layer closed-loop control, significantly improving the PBF process.
- Open Access
- 1 September 2021
- Published by Elsevier in Signal Processing: Image Communication
- Vol. 97
Comprehensive performance analysis of objective quality metrics for digital holography
- 1 September 2021
- Published by Elsevier in Signal Processing: Image Communication
- Vol. 97
Open AccessComprehensive performance analysis of objective quality metrics for digital holography
- 20 November 2020
- Published by Optica Publishing Group in Optics Express
- Vol. 28 (24) , 37069-37091
Suitability analysis of holographic vs light field and 2D displays for subjective quality assessment of Fourier holograms
Measuring the impact of compression on the reconstruction quality of holograms remains a challenge. A public subjectively-annotated holographic data set that allows for testing the performance of compression techniques and quality metrics is presented, in addition to a subjective visual quality assessment methodology. Moreover, the performance of the quality assessment procedures is compared for holographic, regular 2D and light field displays. For these experiments, a double-stimulus, multi-perspective, multi-depth testing methodology was designed and implemented. Analysis of the quality scores indicated that in the absence of a suitable holographic display and under the presented test conditions, non-holographic displays can be deployed to display numerically reconstructed holograms for visual quality assessment tasks.
- 20 November 2020
- Published by Optica Publishing Group in Optics Express
- Vol. 28 (24) , 37069-37091
Suitability analysis of holographic vs light field and 2D displays for subjective quality assessment of Fourier holograms
Measuring the impact of compression on the reconstruction quality of holograms remains a challenge. A public subjectively-annotated holographic data set that allows for testing the performance of compression techniques and quality metrics is presented, in addition to a subjective visual quality assessment methodology. Moreover, the performance of the quality assessment procedures is compared for holographic, regular 2D and light field displays. For these experiments, a double-stimulus, multi-perspective, multi-depth testing methodology was designed and implemented. Analysis of the quality scores indicated that in the absence of a suitable holographic display and under the presented test conditions, non-holographic displays can be deployed to display numerically reconstructed holograms for visual quality assessment tasks.
- Open Access
Comprehensive Performance Analysis of Objective Quality Metrics for Digital Holography
Objective quality assessment of digital holograms has proven to be a challenging task. While prediction of perceptual quality of the recorded 3D content from the holographic wavefield is an open problem; perceptual quality assessment from content after rendering, requires a time-consuming rendering step and a multitude of possible viewports. In this research, we use 96 Fourier holograms of the recently released HoloDB database to evaluate the performance of well-known and state-of-the-art image quality metrics on digital holograms. We compare the reference holograms with their distorted versions: (i) before rendering on the real and imaginary parts of the quantized complex-wavefield, (ii) after converting Fourier to Fresnel holograms, (iii) after rendering, on the quantized amplitude of the reconstructed data, and (iv) after subsequently removing speckle noise using a Wiener filter. For every experimental track, the quality metric predictions are compared to the Mean Opinion Scores (MOS) gathered on a 2D screen, light field display and a holographic display. Additionally, a statistical analysis of the results and a discussion on the performance of the metrics are presented. The tests demonstrate that while for each test track a few quality metrics present a highly correlated performance compared to the multiple sets of available MOS, none of them demonstrates a consistently high-performance across all four test-tracks.
Open AccessComprehensive Performance Analysis of Objective Quality Metrics for Digital Holography
Objective quality assessment of digital holograms has proven to be a challenging task. While prediction of perceptual quality of the recorded 3D content from the holographic wavefield is an open problem; perceptual quality assessment from content after rendering, requires a time-consuming rendering step and a multitude of possible viewports. In this research, we use 96 Fourier holograms of the recently released HoloDB database to evaluate the performance of well-known and state-of-the-art image quality metrics on digital holograms. We compare the reference holograms with their distorted versions: (i) before rendering on the real and imaginary parts of the quantized complex-wavefield, (ii) after converting Fourier to Fresnel holograms, (iii) after rendering, on the quantized amplitude of the reconstructed data, and (iv) after subsequently removing speckle noise using a Wiener filter. For every experimental track, the quality metric predictions are compared to the Mean Opinion Scores (MOS) gathered on a 2D screen, light field display and a holographic display. Additionally, a statistical analysis of the results and a discussion on the performance of the metrics are presented. The tests demonstrate that while for each test track a few quality metrics present a highly correlated performance compared to the multiple sets of available MOS, none of them demonstrates a consistently high-performance across all four test-tracks.
- Open Access
- 9 November 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 27 (2) , 879-893
From Sparse Coding Significance to Perceptual Quality: A New Approach for Image Quality Assessment
An increasing number of image processing applications require an automated quality prediction of the visual content as perceived by humans. Since, sparse coding is suggested to be an underlying strategy of the brain’s neural system, it would be logical to assume that specific tasks like quality assessment also attempt to adhere to this strategy. However, existing perceptual quality predictors, often mimicking the different stages of the human visual system and deploying machine learning strategies, such as neural networks, rarely integrate the concept of sparse coding in their design. In this paper, we first investigate the validity of such assumption by performing an empirical analysis on the relation between the structural information of the scene—captured via sparseness significance—and perceptual quality. Subsequently, we propose a new approach to integrate the significance of sparse coding features in the future imagequality measure (IQM) designs. We utilize the Fourier transform as a case study, which leads to a new IQM called sparseness significance ranking measure (SSRM). This measure essentially deploys a Fourier basis for sparse coding, a ranking mechanism based upon the amplitudes of the sparse coefficients and subsequently a complex correlation metric that assesses the correspondence between the ranked coefficient amplitude profiles of the reference and the distorted image. Moreover, we introduce a new methodology, namely separation ratio analysis, to assess the prediction quality of individual features or quality predictors given a target perceptual quality. The quality predictions by the proposed SSRM show excellent compatibility with perceptual quality scores. A set of routine benchmarking experiments utilizing the LIVE and CSIQ, IVC and TID2008 databases indicates a highly competitive performance with state of the art IQMs. Moreover, it delivers this performance at a low computational cost.
- 9 November 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 27 (2) , 879-893
Open AccessFrom Sparse Coding Significance to Perceptual Quality: A New Approach for Image Quality Assessment
An increasing number of image processing applications require an automated quality prediction of the visual content as perceived by humans. Since, sparse coding is suggested to be an underlying strategy of the brain’s neural system, it would be logical to assume that specific tasks like quality assessment also attempt to adhere to this strategy. However, existing perceptual quality predictors, often mimicking the different stages of the human visual system and deploying machine learning strategies, such as neural networks, rarely integrate the concept of sparse coding in their design. In this paper, we first investigate the validity of such assumption by performing an empirical analysis on the relation between the structural information of the scene—captured via sparseness significance—and perceptual quality. Subsequently, we propose a new approach to integrate the significance of sparse coding features in the future imagequality measure (IQM) designs. We utilize the Fourier transform as a case study, which leads to a new IQM called sparseness significance ranking measure (SSRM). This measure essentially deploys a Fourier basis for sparse coding, a ranking mechanism based upon the amplitudes of the sparse coefficients and subsequently a complex correlation metric that assesses the correspondence between the ranked coefficient amplitude profiles of the reference and the distorted image. Moreover, we introduce a new methodology, namely separation ratio analysis, to assess the prediction quality of individual features or quality predictors given a target perceptual quality. The quality predictions by the proposed SSRM show excellent compatibility with perceptual quality scores. A set of routine benchmarking experiments utilizing the LIVE and CSIQ, IVC and TID2008 databases indicates a highly competitive performance with state of the art IQMs. Moreover, it delivers this performance at a low computational cost.