Abstract: Chromosome characterization is crucial in cytogenetic research and diagnostics, necessitating precise imaging methods to ensure proper analyses. The aim of this project is to identify a reliable method for chromosomal characterization that uses hyperspectral imagery of stained metaphase chromosomes using bright-field microscopy. We analyzed four hyperspectral images of stained chromosomes acquired under bright-field illumination. To address the high dimensionality of the hyperspectral hypercubes, we applied five dimension reduction algorithms based on spectral band selection to determine the most effective approach. A comparative study was conducted between five band selection methods to assess their effectiveness in chromosome characterization. The results indicate that sparse subspace clustering and multi-objective band selection are the most effective methods, outperforming the others in reducing the spectral dimensionality of the hyperspectral data, while preserving key properties essential for accurate chromosomes characterization. This study demonstrates that careful selection of spectral bands can enhance the analysis of spectral hypercubes for chromosome characterization.

New from Applied Spectroscopy!
Exploring Band Selection Methods for Enhanced Chromosomal Analysis in Hyperspectral Imaging
Read more: https://doi.org/10.1177/00037028251403574
#SAS #Spectroscopy #Hyperspectral #Band #Selection #Chromosomal #Analysis

Do YOU need more #PACE #hyperspectral in your life? 🤔 Then sign up for the PACE [virtual] applications workshop next week (11th-12th March 2026). Registration: www.eventbrite.com/e/pace-appli...

#KeepingPACE

Another nice work from Salma, this time on the training of classifiers for #hyperspectral images under limited data conditions.

#HSI #AI #ML
#sqIRL #IDLab #UAntwerp #imec

Enhancing hyperspectral image prediction with contrastive learning in low-label regimes - Applied Intelligence Labelled data scarcity remains a longstanding challenge in hyperspectral image analysis, primarily due to high spectral dimensionality and the laborious nature of manual annotation. Self-supervised co...

Interested in training hyperspectral image analysis models with reduced annotated data?
Salma explores this question in her recent paper.
doi.org/10.1007/s104...

#hyperspectral #HSI #AI #ML #ContrastiveLearning
#sqIRL #IDLab #UAntwerp #imec

The results highlight pathways to advance hyperspectral & enhanced multispectral products (e.g., plant N, SOC, species, water quality) from prototype (TRL 4–6) to policy-ready services via stronger science–policy interfaces and co-design.


#EO #Copernicus #Hyperspectral #RemoteSensing

Abstract: The increasing concern about the presence of pesticides in vegetable leaves has underscored an urgent need for real-time, nondestructive, and accurate detection methods. Traditional methods are reliable but laboratory-based, costly, and unsuitable for field monitoring. In this study, we propose an efficient learning model pipeline that uses hyperspectral reflectance signatures to detect pesticide residue in plant leaves. We extract a comprehensive set of 39 domain-specific features based on vegetation indices, red-edge metrics, spectral statistics, and derivative profiles. To enhance the performance, use a multilayer perceptron to extract more features. A feature fusion module is used to combine both domain-specific features and features extracted by a multilayer perceptron. Further refinement is achieved through a feed-forward attention scoring module that dynamically weights important features. The efficiency of the system is evaluated using an enhanced extra trees classifier, which shows superior classification performance and stability across different feature formats. With cross-validation, our model achieves an accuracy of 94.69%, significantly outperforming conventional classifiers such as convolutional neural networks, support vector machines, and ensemble models such as random forest and extra trees. This framework not only improves interpretability and performance but also provides a foundation for a real-time, on-site pesticide monitoring solution.

New from Applied Spectroscopy!
Advanced #Hyperspectral Signature Processing for Chemical Stress Detection in #Vegetable Leaves Using #Hierarchical #Feature Extraction and #Enhanced #Ensemble #Model
Read more: https://doi.org/10.1177/00037028251411953
#SAS #Spectroscopy #pesticides #vegetable

a man with glasses is surrounded by a glowing circle and the website pmitf.com is displayed below him ALT: a man with glasses is surrounded by a glowing circle and the website pmitf.com is displayed below him

Them: "Have you looked at the #hyperspectral data from NASA's PACE OCI (pace.oceansciences.org/oci.htm )?"

Me: "But it's an Ocean Color Instrument and I'm all about land."

Them: "It also monitors the land."

Me:

Via #OPG_Optica: PCA-based polynomial transmission filter design for spectral imaging https://bit.ly/4q5yBvJ #OpticalTransmissionFilters #Hyperspectral 💡⚛️

Congrats Salma, well deserved.
Thanks for all your efforts and positive energy.
Lots of success on your future endeavors.
#AI #ML #HSI #Hyperspectral #deeplearning
#sqIRL #UAntwerp #imec

Time to celebrate!
Last week Salma successfully defended her PhD on #Representation #Learning for #Hyperspectral Image Analysis.

Thanks for the cool research, your support to the members of the group, and all your contributions to #sqIRL/#IDLab.

Congratulations Dr. Haidar

#HSI #AI #ML #UAntwerp

RGB is for displays, not for physics.
Hyperspectral rendering + sensor-aware synthetic data lets models see differences RGB hides (metamerism, narrowband cues, illuminant shifts).
We treat light as λ, not 3 guesses.

#Hyperspectral #ComputerVision #SyntheticData

Abstract This study proposes a method to remove background pixels from near-infrared hyperspectral images based on the pixel-wise standard deviation of reflectance method (px-wise SD method). This method calculates the standard deviation (SD) of reflectance in each pixel, namely each spectrum, and determines a threshold to distinguish between background and object pixels from the resulting histogram of the px-wise SD. The method effectiveness is evaluated using hyperspectral images of a leaf-like pastry with a hole placed on either a low-reflectance sheet or white paper. On white paper, the px-wise SD of reflectance exhibits a trimodal histogram with two prominent peaks and one small peak between them. The prominent peak with a lower SD corresponds to the white paper pixels, whereas the other peak with a higher SD is associated with the surface and edge pixels of the pastry. The small peak represents the pixels of the hole. The background and object pixels can be effectively separated by setting a threshold between this small peak and the prominent peak for the pastry pixels. Moreover, the mean spectrum calculated using only object pixels remains consistent, regardless of the type of background material. Conversely, the mean spectrum calculated using all pixels is distorted due to the spectral inclusion of the background material.

New from Applied Spectroscopy!
Background Pixel Removal for Near-Infrared Hyperspectral Images Based on the Pixel-Wise Standard Deviation of Reflectance
Read Open Access 🔓: https://doi.org/10.1177/00037028251368377
#SAS #Spectroscopy #NIR #hyperspectral #image #remove #background #pixels

Generation of Synthetic Hyperspectral Image Cube for Mapping Soil Organic Carbon Using Proximal Remote Sensing
www.mdpi.com/3042-5743/36...

By Rajan G. Rejith et al.
From the 2nd International Electronic Conference on Land

#Hyperspectral #SoilCarbon #MachineLearning

Abstract Tropical mosquitoes transmit diseases like malaria, yellow fever, and Zika. Classifying mosquitoes by species, sex, age, and gravidity offers vital insights for assessing transmission risk and effective mitigations. Photonic monitoring for mosquito classification can be used in distributed sensors or lidars on longer ranges. However, a reflectance model and its parameters are lacking in the current literature. This study investigates mosquitoes of different species, sexes, age groups, and gravidity states, and reports metric pathlengths of wing chitin, body melanin, and water. We use hyperspectral push-broom imaging and laser multiplexing with a rotation stage to measure near-infrared spectra from different angles and develop simple models for spectral reflectance, including wing thickness and equivalent absorption path lengths for melanin and water. We demonstrate wing thickness of 174 (±1) nm – the thinnest wings reported to our knowledge. Water and melanin pathlengths are determined with ∼10 µm precision, and spectral models achieve adjusted R² values exceeding 95%. While mosquito aspect angle impacts the optical cross-section, it alters shortwave infrared spectra minimally (∼2%). These results demonstrate the potential for remote retrieval of micro- and nanoscopic mosquito features using spectral sensors and lidars irrespective of insect body orientation. Improved specificity of vector monitoring can be foreseen.

New from Applied Spectroscopy!
Deadliest Animals with the Thinnest Wings: Near-Infrared Properties of Tropical Mosquitoes
Read open access 🔓: https://doi.org/10.1177/00037028251341317
#SAS #Spectroscopy #NIR #mosquitoes #spectral #reflectance #remote #hyperspectral

Hyperspectral Imaging System Market Size, Growth Report 2035 Hyperspectral Imaging System Market Size is projected to grow from 7.9 USD Bn in 2025 to 23.0 USD Bn by 2035, exhibiting a CAGR of 11.2 during 2025 - 2035.

📡 Hyperspectral Imaging Market sees growth in healthcare & defense. Report: www.marketresearchfuture.com/reports/hype... #Hyperspectral #ImagingTech

Image of finger clip with apertures for light, hyperspectral camera (HSC) and spectrometer. A scheme, indicating that the computer analyzes the combined signals from the HSC and spectrometer. A graph, indicating a good correlation (k=0.92) between the true and predicted values of HGB-Model 3 in blood. Text Box: Conclusion: Spectrometers have low amplitude resolution and accuracy, while HSPs suffer from limited number of wavelength channels. To solve this, we propose a method of acquiring spectrometer data combined with HSP and modelling the data. This combines the advantages of both, and effectively improves the accuracy of the non-invasive blood components measurements.

New from Applied Spectroscopy!
Combining a #Multispectral Camera and #Spectrometer for #Spectral Data Acquisition and #Noninvasive Blood Composition Measurement

#SAS #Spectroscopy #bloodanalysis #hyperspectral

We just released EnMAP-Box 3.17.1, bringing numerous new features and improvements. For example, the new Spectral Index Explorer visualizes numerous spectral indices on-the-fly with just a mouse click. #EnMAP #Hyperspectral #ImagingSpectroscopy

#Pixxel joins #UP42 to provide 5 m #hyperspectral imagery from the Firefly constellation, covering 135+ spectral bands for agriculture, climate and forestry.

🔗 spacewatch.global/2025/12/pixxel-and-up42-...

#SpaceWatchNews #EO

Abisko Sweden looking over Torneträsk

📢 Do you want to do a #PhD using #hyperspectral satellite data to observe climate influences on tundra vegetation in Sweden? With me and @robertgbjork.bsky.social at U of Gothenburg. Apply by 19 Jan 2026. bit.ly/44duvJI

Not sure where this is, but it's a spectacular #hyperspectral image from #Wyrvern. They're an #Edmonton satellite company!
Sample images for download here https://opendata.wyvern.space

Research Team at BIFOLD/ @tuberlin.bsky.social developed a new #hyperspectral image compression model called #HyCASS.

Published in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing

#RemoteSensing #GISchat #AdvancedImaging #EerthObservation #EO #geoObserver

A free tool for geologists and remote sensing enthusiasts.
🔬 Spectral Analysis
🛰️ Hyperspectral Imagery
📊 Open Science

🚀 Developed in Python
💻 Standalone GUI
🎯 Designed for VNIR–SWIR raster data

🔗 doi.org/10.3390/a180...
#RemoteSensing #Geology #Hyperspectral #Python

Wyvern Hyperspectral Data Visualization Made Easy

Learn how to easily visualize high-resolution hyperspectral imagery from Wyvern using the HyperCoast Python package.

Notebook example: hypercoast.org/examples/wyv...
Wyvern Open Data: wyvern.space/open-data

#Wyvern #Hyperspectral

Waverider: Scanning Spectra One Pixel at a Time Hyperspectral cameras aren’t commonplace items; they capture spectral data for each of their pixels. While commercial hyperspectral cameras often s...

#hardware #camera #hyperspectral #pi #pico #single #pixel […]

[Original post on hackaday.com]

Waverider: Scanning Spectra One Pixel at a Time Hyperspectral cameras aren’t commonplace items; they capture spectral data for each of their pixels. While commercial hyperspectral cameras often s...

#hardware #camera #hyperspectral #pi #pico #single #pixel […]

[Original post on hackaday.com]

Robotic System Maps Vineyard Grape Yield with Illumination‑Invariant AI

Robotic platform maps vineyard grape yield; model recall 0.82. It estimates bunch weight (R² 0.76), streams data to cloud, and creates yield and quality maps. Read more: getnews.me/robotic-system-maps-vine... #precisionviticulture #hyperspectral