Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Electrically Tunable Tunneling and Spectral Response in WSe<sub>2</sub>/h-BN/CdSe/Graphene Heterostructure.

Small (Weinheim an der Bergstrasse, Germany)·2026

Same author

Left ventricular unloading during extracorporeal cardiopulmonary resuscitation: a target trial emulation of the ELSO registry.

Critical care (London, England)·2025

Same author

Strategies for integrating animal social learning and culture into conservation translocation practice.

Philosophical transactions of the Royal Society of London. Series B, Biological sciences·2025

Same author

Driven bright solitons on a mid-infrared laser chip.

Nature·2025

Same author

A cross-sectional study of the role of epithelial cell injury in kidney transplant outcomes.

JCI insight·2025

Same author

Machine learning to optimize use of natriuretic peptides in the diagnosis of acute heart failure.

European heart journal. Acute cardiovascular care·2025

Search research articles

Related Experiment Video

Updated: Aug 31, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

A photosensor employing data-driven binning for ultrafast image recognition.

Lukas Mennel¹, Aday J Molina-Mendoza¹, Matthias Paur¹

¹Institute of Photonics, Vienna University of Technology, Gußhausstraße 27-29, 1040, Vienna, Austria.

Scientific Reports

|August 24, 2022

Summary

Researchers developed a novel "superpixel" approach, pushing pixel binning limits for enhanced optical sensing. This method achieves high-accuracy image classification and spectroscopy with improved dynamic range, reducing data processing needs.

More Related Videos

Lensless Fluorescent Microscopy on a Chip

Lensless Fluorescent Microscopy on a Chip

Published on: August 17, 2011

Fabrication of Flexible Image Sensor Based on Lateral NIPIN Phototransistors

Fabrication of Flexible Image Sensor Based on Lateral NIPIN Phototransistors

Published on: June 23, 2018

Related Experiment Videos

Last Updated: Aug 31, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

Lensless Fluorescent Microscopy on a Chip

Lensless Fluorescent Microscopy on a Chip

Published on: August 17, 2011

Fabrication of Flexible Image Sensor Based on Lateral NIPIN Phototransistors

Fabrication of Flexible Image Sensor Based on Lateral NIPIN Phototransistors

Published on: June 23, 2018

Area of Science:

Optics and Photonics
Machine Learning
Image Processing

Background:

Pixel binning is a standard technique in optical image acquisition and spectroscopy.
It combines adjacent detector elements to reduce data and noise but sacrifices information.
Existing methods face limitations in data processing and dynamic range.

Purpose of the Study:

To explore the extreme limits of pixel binning by creating a single "superpixel" covering an entire sensor.
To investigate the application of machine learning in optimizing superpixel shape for specific pattern recognition tasks.
To demonstrate enhanced performance in optical image classification and sensing applications.

Main Methods:

Developed a "superpixel" by combining a large fraction of sensor elements.
Utilized a machine learning algorithm to determine the optimal superpixel shape from training data.
Applied the superpixel concept to classify images from the MNIST dataset.

Main Results:

Achieved accurate classification of projected images from the MNIST dataset on a nanosecond timescale.
Demonstrated enhanced dynamic range in the superpixel sensing approach.
Showcased no loss of classification accuracy compared to traditional methods.

Conclusions:

The superpixel concept effectively pushes pixel binning to its limits, offering significant advantages.
This approach enhances dynamic range and maintains classification accuracy for optical sensing tasks.
The technique is versatile and applicable to optical imaging, spectroscopy, and other sensing domains.