A5036753987- Industrial Vision Systems and Defect Detection
- Electron and X-Ray Spectroscopy Techniques
- Advanced Neural Network Applications
- Blind Source Separation Techniques
- Tensor decomposition and applications
- Image Processing Techniques and Applications
- Machine Learning in Materials Science
- Optical Imaging and Spectroscopy Techniques
- Human Pose and Action Recognition
- Gene expression and cancer classification
- Integrated Circuits and Semiconductor Failure Analysis
- Engineering Education and Technology
- Digital Transformation in Industry
- Cardiovascular Health and Disease Prevention
- Spectroscopy and Chemometric Analyses
- Ocean Waves and Remote Sensing
- Anomaly Detection Techniques and Applications
- Advancements in Photolithography Techniques
- Economic and Technological Systems Analysis
- Sparse and Compressive Sensing Techniques
- Advanced Electron Microscopy Techniques and Applications
Laboratoire d'Informatique, de Modélisation et d'Optimisation des Systèmes
2025
Université de Bourgogne
2024
ImViA - Imagerie et Vision Artificielle
2023
Aix-Marseille Université
2021-2022
Laboratoire d’Informatique et Systèmes
2021-2022
Institut Méditerranéen d’Océanologie
2022
Laboratoire d'Informatique Fondamentale et Appliquée de Tours
2019
Université de Tours
2019
Precision characterization is fundamental to achieve expected performance in semiconductors where Moore's law pushes the boundaries miniaturize components. To measure these attributes, deep learning models are used, which require manual annotation of several objects captured via electron microscopy. However, this can be laborious and time-consuming. We propose a semi-automated method for annotating items microscopy images, an effort innovative, efficient, reliable. Our approach involves...
Deep learning models have been proven to automate metrology tasks. It provides accurate, robust and fast results if it is trained with proper data. Nonetheless, obtaining training data remains tedious. requires an expert user delimitate objects boundaries in several images representing tens hundreds of objects. Instead drawing precise boundaries, we propose a tool relying on rectangular bounding box detect segment For complex applications non-homogeneous background, the must draw one per...
Human action Recognition has been extensively addressed by deep learning. However, the problem is still open and many learning architectures show some limits, such as extracting redundant spatio-temporal informations, using hand-crafted features, instability of proposed networks on different datasets. In this paper, we present a general method for human recognition. This model fits any type database apply it CAD-120 which complex dataset. Our thus clearly improves in two aspects. The first...
The Nonnegative Canonical Polyadic Decomposition (NN-CPD) is now widely used in signal processing to decompose multi-way arrays thanks nonnegative factor matrices. In many applications, a three way array built from collections of 2D-signals and new signals are regularly recorded. this case one may want update the matrices after each measurement without computing NN-CPD whole array. We then speak Online NN-CPD. context main difficulty that number relevant factors unknown can vary with time....
For semiconductor applications, billions of objects are manufactured for a single device such as central processing unit (CPU), storage drive, or graphical (GPU). To obtain functional devices, each element the has to follow precise dimensional and physical specifications at nanoscale. Generally, pipeline consists annotate an object in image then take measurements object. Manually annotating images is extremely time-consuming. In this paper, we propose robust fast semi-automatic method...