Jean-Baptiste Fasquel
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jean-Baptiste Fasquel has a total of 36 co-authors. Here are the top co-authors by number of shared publications:
- Mickael Dinomais
Univ Angers, LARIS, SFR MATHSTIC, Mdecine physique et de radaptation, CHU,Angers,France
4 shared publications - Patty Coupeau
Université d'Angers, LARIS, SFR MATHSTIC, F-49000 Angers, France
4 shared publications - Anne Humeau-Heurtier
Univ Angers, LARIS, SFR MATHSTIC, F-49000, Angers, France
2 shared publications - Clément Veyer
Univ Angers, LARIS SFR MATHSTIC,Angers,France,F-49000
2 shared publications - Harold Mouchère
Nantes Université, École Centrale Nantes, CNRS, LS2N, UMR 6004
2 shared publications - Isabelle Bloch
Sorbonne Universite
2 shared publications
Latest Publications
- 13 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
A Multi-View Graph Approach for Morphometry-Aware Semantic Image Segmentation
This paper extends the use of graph neural networks (GNN) to improve semantic segmentation with limited input data. After segmenting structures using a convolutional neural network (CNN), we propose to model the spatial relationships between the segmented regions through a graph. Then, we refine the suboptimal segmentation with a node classification. We consider a multi-view approach, one view regarding the probabilistic belonging predicted by the CNN, and the second view regarding regions' morphometry. This leads to a morphometryaware GNN. Two strategies are explored: a late-fusion one, consisting of two parallel GNNs, where each one receives a different view of the graph representing the segmented structures as input, and an early-fusion one, where node features are just a concatenation of the views. Experiments are conducted on both a synthetic and a medical dataset, including healthy and injured children's brain MRIs. Our method demonstrates superior performance on both datasets compared to the baseline, achieving a gain of 7% in accuracy compared to previous work on the synthetic dataset, a gain of 25% in Hausdorff distance on the medical dataset for healthy children, and a 15% gain for injured ones. When training data is limited to 12% of the whole training subset, we measure a gain of 64% for healthy children and of 26% for injured ones, emphasizing the robustness of the method integrating morphometric information in a multi-view manner.
- 13 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
A Multi-View Graph Approach for Morphometry-Aware Semantic Image Segmentation
This paper extends the use of graph neural networks (GNN) to improve semantic segmentation with limited input data. After segmenting structures using a convolutional neural network (CNN), we propose to model the spatial relationships between the segmented regions through a graph. Then, we refine the suboptimal segmentation with a node classification. We consider a multi-view approach, one view regarding the probabilistic belonging predicted by the CNN, and the second view regarding regions' morphometry. This leads to a morphometryaware GNN. Two strategies are explored: a late-fusion one, consisting of two parallel GNNs, where each one receives a different view of the graph representing the segmented structures as input, and an early-fusion one, where node features are just a concatenation of the views. Experiments are conducted on both a synthetic and a medical dataset, including healthy and injured children's brain MRIs. Our method demonstrates superior performance on both datasets compared to the baseline, achieving a gain of 7% in accuracy compared to previous work on the synthetic dataset, a gain of 25% in Hausdorff distance on the medical dataset for healthy children, and a 15% gain for injured ones. When training data is limited to 12% of the whole training subset, we measure a gain of 64% for healthy children and of 26% for injured ones, emphasizing the robustness of the method integrating morphometric information in a multi-view manner.
- 13 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Multi-View Dispersion Entropy on Graphs: Application to the Detection of Cerebral Palsy After Neonatal Stroke
In this work, we present a novel method for quantifying irregularity in multi-view graph signals. This approach leverages the concept of dispersion entropy to measure disorder across multiple node-attribute views, while maintaining a fixed graph topology. Moreover, the ensemble dispersion entropy on graphs is proposed to obtain robust results. When applied to graphs computed from brain MRI of children (children with or without cerebral palsy), the results show a higher dispersion entropy for graphs of brain structures from pathological children. This emphasizes the disorder present in the brain of subjects suffering from cerebral palsy. Compared to recently obtained results using graph neural networks, the proposed hand-crafted approach has the advantage of being explicit and not relying on a training dataset. This work lays the foundation for a broader use of dispersion entropy in multi-view graph analysis, with promising applications in neuroscience.
- 13 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Multi-View Dispersion Entropy on Graphs: Application to the Detection of Cerebral Palsy After Neonatal Stroke
In this work, we present a novel method for quantifying irregularity in multi-view graph signals. This approach leverages the concept of dispersion entropy to measure disorder across multiple node-attribute views, while maintaining a fixed graph topology. Moreover, the ensemble dispersion entropy on graphs is proposed to obtain robust results. When applied to graphs computed from brain MRI of children (children with or without cerebral palsy), the results show a higher dispersion entropy for graphs of brain structures from pathological children. This emphasizes the disorder present in the brain of subjects suffering from cerebral palsy. Compared to recently obtained results using graph neural networks, the proposed hand-crafted approach has the advantage of being explicit and not relying on a training dataset. This work lays the foundation for a broader use of dispersion entropy in multi-view graph analysis, with promising applications in neuroscience.
- 14 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 01-06
Multi-View Graph Neural Network for Semantic Image Segmentation
Semantic image segmentation is a fundamental task in computer vision, frequently addressed using deep learning techniques. Nevertheless, these methods often struggle to fully capture the structural details and semantic relationships present within an image. We propose a new approach, based on a multiview graph neural network, allowing to exploit various kinds of structural information, each one being related to a particular view. We perform experiments on both a synthetic dataset and a real-world one and demonstrate that our model is superior to conventional graph neural network and resilient to small training datasets. Subsequently, our method outperforms other classic methods when considering a few training data. Additionally, the integration of views appears to improve convergence in training. Our findings highlight the potential of multi-view representations in enhancing image segmentation tasks, paving the way for more advanced and accurate computer vision systems.
- 14 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 01-06
Multi-View Graph Neural Network for Semantic Image Segmentation
Semantic image segmentation is a fundamental task in computer vision, frequently addressed using deep learning techniques. Nevertheless, these methods often struggle to fully capture the structural details and semantic relationships present within an image. We propose a new approach, based on a multiview graph neural network, allowing to exploit various kinds of structural information, each one being related to a particular view. We perform experiments on both a synthetic dataset and a real-world one and demonstrate that our model is superior to conventional graph neural network and resilient to small training datasets. Subsequently, our method outperforms other classic methods when considering a few training data. Additionally, the integration of views appears to improve convergence in training. Our findings highlight the potential of multi-view representations in enhancing image segmentation tasks, paving the way for more advanced and accurate computer vision systems.
- 2 June 2022
- Published by Springer Nature
- p. 173-184
Improving Semantic Segmentation with Graph-Based Structural Knowledge
- 2 June 2022
- Published by Springer Nature
- p. 173-184
Improving Semantic Segmentation with Graph-Based Structural Knowledge
- 2 June 2022
- Published by Springer Nature
- p. 47-58
QAP Optimisation with Reinforcement Learning for Faster Graph Matching in Sequential Semantic Image Analysis
- 2 June 2022
- Published by Springer Nature
- p. 47-58
QAP Optimisation with Reinforcement Learning for Faster Graph Matching in Sequential Semantic Image Analysis
- 19 April 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
On the relevance of edge-conditioned convolution for GNN-based semantic image segmentation using spatial relationships
This paper addresses the fundamental task of semantic image segmentation by exploiting structural information (spatial relationships between image regions). To perform such task, we propose to combine a deep neural network (CNN) with inexact “many-to-one-or-none” graph matching where graphs encode efficiently class probabilities a nd structural information related to regions segmented by the CNN. In order to achieve node classification, a basic 2 -layer graph neural network (GNN) based on the edge-conditioned convolution operator (ECConv), managing both node and edge attributes, is considered. Prelim-inary experiments are performed on both a synthetic dataset and a public dataset of face images (FASSEG). Our approach is shown to be resilient to small training datasets that often limit the performance of deep learning thanks to a preprocessing task of graph coarsening. Results show that the proposal reaches a perfect accuracy on synthetic dataset and improves performance of the CNN by 6% (bounding box dice index) on FASSEG. Moreover, it enhances by 27% the initial Hausdorff distance (i.e. with CNN only) using the entire training dataset and by 41% with only 75% of training samples.
- 19 April 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
On the relevance of edge-conditioned convolution for GNN-based semantic image segmentation using spatial relationships
This paper addresses the fundamental task of semantic image segmentation by exploiting structural information (spatial relationships between image regions). To perform such task, we propose to combine a deep neural network (CNN) with inexact “many-to-one-or-none” graph matching where graphs encode efficiently class probabilities a nd structural information related to regions segmented by the CNN. In order to achieve node classification, a basic 2 -layer graph neural network (GNN) based on the edge-conditioned convolution operator (ECConv), managing both node and edge attributes, is considered. Prelim-inary experiments are performed on both a synthetic dataset and a public dataset of face images (FASSEG). Our approach is shown to be resilient to small training datasets that often limit the performance of deep learning thanks to a preprocessing task of graph coarsening. Results show that the proposal reaches a perfect accuracy on synthetic dataset and improves performance of the CNN by 6% (bounding box dice index) on FASSEG. Moreover, it enhances by 27% the initial Hausdorff distance (i.e. with CNN only) using the entire training dataset and by 41% with only 75% of training samples.
- 3 April 2020
- Published by Springer Nature
- p. 67-76
Towards a Smartwatch for Cuff-Less Blood Pressure Measurement Using PPG Signal and Physiological Features
- 3 April 2020
- Published by Springer Nature
- p. 67-76
Towards a Smartwatch for Cuff-Less Blood Pressure Measurement Using PPG Signal and Physiological Features
- 11 May 2018
- Published by Optica Publishing Group in Journal of the Optical Society of America A
- Vol. 35 (6) , 936-945
Approach for sequential image interpretation using a priori binary perceptual topological and photometric knowledge and k-means-based segmentation
The proposed approach exploits a priori known qualitative inclusion and photometric relationships between image regions, represented by oriented graphs. Our work assumes a sequential image segmentation procedure where regions are progressively segmented and recognized by associating them with corresponding nodes in graphs related to the prior knowledge. The main contribution concerns the parameterization of the -means clustering algorithm, to be used during the segmentation procedure, and the graph-matching-based identification of resulting clusters, corresponding to regions declared in graphs. The parameterization of -means is based on known relationships as well as on regions that have been segmented and recognized at previous steps. Parameters are the region of interest within which -means clustering is constrained, the number of clusters, and seeding constraints. Photometric relationships built from resulting clusters are matched with a priori known relationships to identify each cluster, this being formulated as an exact graph-matching problem. The potential of this approach is studied in four use cases involving real gray-scale and color images with dedicated sequential analysis procedures. Processing results are compared with those obtained without the proposed parameterization of -means, as well as with some other clustering approaches. Results show the relevance of our approach, in particular in terms of segmentation accuracy, computation time, and seeding reliability.- 11 May 2018
- Published by Optica Publishing Group in Journal of the Optical Society of America A
- Vol. 35 (6) , 936-945
Approach for sequential image interpretation using a priori binary perceptual topological and photometric knowledge and k-means-based segmentation
The proposed approach exploits a priori known qualitative inclusion and photometric relationships between image regions, represented by oriented graphs. Our work assumes a sequential image segmentation procedure where regions are progressively segmented and recognized by associating them with corresponding nodes in graphs related to the prior knowledge. The main contribution concerns the parameterization of the -means clustering algorithm, to be used during the segmentation procedure, and the graph-matching-based identification of resulting clusters, corresponding to regions declared in graphs. The parameterization of -means is based on known relationships as well as on regions that have been segmented and recognized at previous steps. Parameters are the region of interest within which -means clustering is constrained, the number of clusters, and seeding constraints. Photometric relationships built from resulting clusters are matched with a priori known relationships to identify each cluster, this being formulated as an exact graph-matching problem. The potential of this approach is studied in four use cases involving real gray-scale and color images with dedicated sequential analysis procedures. Processing results are compared with those obtained without the proposed parameterization of -means, as well as with some other clustering approaches. Results show the relevance of our approach, in particular in terms of segmentation accuracy, computation time, and seeding reliability.- 17 April 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 41 (5) , 1043-1055
A Graph Based Image Interpretation Method Using A Priori Qualitative Inclusion and Photometric Relationships
This paper presents a method for recovering and identifying image regions from an initial oversegmentation using qualitative knowledge of its content. Compared to recent works favoring spatial information and quantitative techniques, our approach focuses on simple a priori qualitative inclusion and photometric relationships such as "region A is included in region B", "the intensity of region A is lower than the one of region B" or "regions A and B depict similar intensities" (photometric uncertainty). The proposed method is based on a two steps" inexact graph matching approach. The first step searches for the best subgraph isomorphism candidate between expected regions and a subset of regions resulting from the initial oversegmentation. Then, remaining segmented regions are progressively merged with appropriate already matched regions, while preserving the coherence with a priori declared relationships. Strengths and weaknesses of the method are studied on various images (grayscale and color), with various intial oversegmentation algorithms (k-means, meanshift, quickshift). Results show the potential of the method to recover, in a reasonable runtime, expected regions, a priori described in a qualitative manner. For further evaluation and comparison purposes, a Python opensource package implementing the method is provided, together with the specifically built experimental database.
- 17 April 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 41 (5) , 1043-1055
A Graph Based Image Interpretation Method Using A Priori Qualitative Inclusion and Photometric Relationships
This paper presents a method for recovering and identifying image regions from an initial oversegmentation using qualitative knowledge of its content. Compared to recent works favoring spatial information and quantitative techniques, our approach focuses on simple a priori qualitative inclusion and photometric relationships such as "region A is included in region B", "the intensity of region A is lower than the one of region B" or "regions A and B depict similar intensities" (photometric uncertainty). The proposed method is based on a two steps" inexact graph matching approach. The first step searches for the best subgraph isomorphism candidate between expected regions and a subset of regions resulting from the initial oversegmentation. Then, remaining segmented regions are progressively merged with appropriate already matched regions, while preserving the coherence with a priori declared relationships. Strengths and weaknesses of the method are studied on various images (grayscale and color), with various intial oversegmentation algorithms (k-means, meanshift, quickshift). Results show the potential of the method to recover, in a reasonable runtime, expected regions, a priori described in a qualitative manner. For further evaluation and comparison purposes, a Python opensource package implementing the method is provided, together with the specifically built experimental database.
- 1 January 2016
- Published by Springer Nature
- p. 125-130
An Aggregation Plateform for IoT-Based Healthcare: Illustration for Bioimpedancemetry, Temperature and Fatigue Level Monitoring
- 1 January 2016
- Published by Springer Nature
- p. 125-130
An Aggregation Plateform for IoT-Based Healthcare: Illustration for Bioimpedancemetry, Temperature and Fatigue Level Monitoring