Hyperspectral Imaging and Machine Learning: Decoding the Spectrum for Advanced Data Analysis
Practical information:
Want to register?
- Prerequisites: Familiarity with general Machine Learning
- Price: Free
Georganiseerd door:
Leertraject
Every digital photograph collapses the richness of reality into three colour channels - red, green and blue. Hidden in the same scene are hundreds of additional wavelengths that carry chemical, structural, and material clues no conventional camera or human eye can perceive. Hyperspectral imaging (HSI) captures this hidden information, and modern machine learning and AI techniques transform it into business value.
In this industry-focused talk, we will:
- Demystify hyperspectral imaging (HSI): show how combining digital imaging with spectroscopy captures hundreds of narrow wavelength bands, transforming a flat, two-dimensional picture into a three-dimensional ‘data cube’ that reveals material details to which ordinary RGB images are blind.
- Tackle the data challenge: outline why HSI’s sheer volume, redundancy and annotation cost have slowed adoption and how today’s AI, especially supervised and self-supervised learning, breaks those barriers.
- Highlight proven applications: from diagnosing plant stress and verifying food quality to detecting micro-defects in manufacturing, monitoring the environment and preserving cultural heritage.
- Share fresh research insights: including contrastive representation learning and explainability-driven band selection, which make HSI models lighter, faster and easier to deploy.
Join us to explore how the fusion of hyperspectral imaging and AI unlocks hidden patterns in data, and why now is the ideal moment to broaden your analytical palette beyond RGB.
Teachers / speakers
Salma Haider
Salma Haidar is a PhD candidate at the University of Antwerp in Belgium, specializing in advanced representation learning for hyperspectral images, with a focus on land cover analysis from remote sensing data. She holds a bachelor's degree in Accounting and Finance from the Lebanese University and a Master's in Money and Banking from the American University of Beirut. She also holds a Postgraduate Diploma in Big Data & Analytics from KU Leuven. A Chartered Financial Analyst (CFA) since 2006, her diverse background enhances her contributions to machine learning and hyperspectral image analysis.
José Oramas
José Oramas is an Assistant Professor at the Internet Data Lab (IDLab) a joint research lab between the University of Antwerp and IMEC. He received his Ph.D. at the Center for Processing Speech and Images (ESAT-PSI)of KU Leuven in April 2015. Earlier he received his engineering degree from Escuela Superior Politecnica del Litoral in Ecuador. During his Ph.D. he conducted research on understanding how groups of elements from the image (objects, object-parts, image regions, trajectories, etc.) interact and how the relationships between them can be exploited to improve artificial visual perception problems. This fueled his interest towards investigating exploratory/explanatory models that can identify informative intermediate representations and use them as means to justify the predictions that they make.
Research Interests: Representation Learning, Interpretability and Explainability, Multiple Instance Learning, Machine Learning, Deep Learning and Computer Vision
Related courses
Fundamental concepts of multi-omics data integration
Opleiding - Leuven - Genomics Core Leuven
