<img alt="" src="https://secure.leadforensics.com/11743.png" style="display:none;">

Non-Visible Imaging: Near-Infrared (NIR)

Welcome to our next series of machine vision blogs! For the next four articles, we will be advancing what we learned from our illumination blog series by exploring the world of non-visible imaging, expanding our knowledge on the fundamentals of light, and looking at camera choice in different non-visible imaging contexts.

This week we will be exploring the use of near-infrared (or near-IR/NIR) imaging in machine vision systems, and how to go about selecting a camera for NIR imaging.

Whether you’re interested in building your own machine vision system for a project, a commercial application, or are just interested in learning more about non-visible imaging for machine vision, this blog post is for you. We hope you enjoy reading!


What is Near-IR (NIR) Imaging?

NIR imaging refers to a range on the light spectrum between 850-940 nanometres (nm).

Visible Light Spectrum + IR

Visible and IR light spectrum.

NIR light has a longer wavelength than visible light, which generally means light is more easily transmitted through materials like paper, cloth and plastic. NIR wavelengths also react differently on materials and coatings than visible light. The key points are that it can:

  • Penetrate materials more easily
  • Reduce colour saturation in imaged objects
  • Cut out unwanted glare and reflections
  • Neglect unwanted details in various inspection applications


NIR Light is used in here to ignore the printed date code and highlight the heater band so it can be inspected.

NIR Filters

Bandpass filters are a great way to ensure only NIR light is reaching the sensor of your camera. MidOpt offer a really good range of machine vision filters, with their BP880 filter offering a useful range of 845-930nm.

MidOpt BP880

MidOpt BP880 Data


NIR imaging can solve problems in a variety of industries, including machine vision, factory automation, security and surveillance, license plate recognition, medicine, and life sciences.

In factory machine vision, NIR illumination is a great for things like inspecting fill levels in packaging. Certain defects and flaw detection can be identified with NIR where visible light does not work.

NIR imaging has also revolutionised automatic number plate recognition (ANPR) technology, assisting in specific applications such as electronic toll collection (ETC), car park management, and law enforcement.

In an ANPR vision system, a high-resolution camera with an NIR illuminator has to clearly image a vehicle’s registration plate. The ingenuity behind using NIR imaging in this application is that regardless of day, night, shaded or well-lit environments, NIR LEDs will always be capable of providing sufficient illumination for the camera to perform its task.

The image can then be analysed on the computer system using Optical Character Recognition (OCR) software. Implementing a deep learning approach here would grant you a robust, autonomous ANPR system that would work in any lighting environment thanks to the use of NIR imaging.


Camera Choice

Before we get carried away, we need to make sure that the camera, and more specifically the sensor, are suited to NIR imaging.

As not all sensors are made for imaging outside the visible light spectrum, it’s important you get this right, otherwise your vision system will not get off the ground. It’s at this point we need to start thinking about the topics we covered in our blog on the EMVA 1288 standard for sensors.

EMVA1288 is a standard that defines what aspects of camera performance to measure, how to measure them and how to present the results in a unified method.

Factors to Consider when Selecting a Camera for NIR Imaging

Quantum Efficiency (QE) for NIR Sensors

Quantum efficiency changes dramatically at different wavelengths, so a camera that performs well at 525nm, may not perform nearly as well when the light source is at NIR frequencies.

Near-Infrared Imaging Performance

The silicon used by CMOS image sensors to detect incoming photons has a relatively low sensitivity to light of wavelengths greater than 900 nm. The average QE for Sony Pregius and STARVIS sensors at 850nm is 18%, while at 950 this falls to 7%.

For applications which benefit from sensitivity in the Near-Infrared (NIR) wavelengths, Pregius and STARVIS sensors are generally recommended. While their QE at 950 nm may be lower than other sensors optimized for higher QE at this wavelength, the far lower Temporal Dark Noise (read noise) of Pregius sensors easily compensates for this.

The low read noise results in Pregius and STARVIS sensors having much better NIR Absolute Sensitivity Threshold. This allows higher gain to be applied, delivering a brighter, clearer image than sensors with higher NIR QE, but lower NIR AST.

Sony IMX265 QE

QE of the Sony IMX265 CMOS sensor, with the NIR region of the spectrum highlighted in red.


EMVA Gain is the number of electrons required to increase the pixel value from a 16-bit greyscale value to one value higher. Sensors with higher gain will appear brighter with fewer electrons. High gain can be useful for detecting very weak signals in low light conditions.

Conclusions for Selecting a Camera for NIR Imaging

What this all boils down to is this: when selecting a camera for NIR imaging, if you’re going off quantum efficiency alone, you may get away with a camera that promises ~50% QE. Relying closely on QE may be logical at typical visible light wavelengths, however what you will find with doing this at NIR wavelengths is that the signal-to-noise (SNR) is often very poor, meaning you end up with an image ruined by temporal dark noise.

The devil is in the detail. By selecting a camera with a sensor recommended for NIR wavelengths, i.e. Sony Pregius and STARVIS, and applying gain, you will end up with a much clearer image than relying on QE values alone.

Machine Vision Solutions for Non-Visible Imaging from ClearView Imaging

That’s it for this week’s blog post on Near-Infrared (NIR) Imaging. Stay tuned for our next blog on Short-Wave Infrared (SWIR) Imaging!

Looking for machine vision components? Be sure to check out our great range of machine vision components over in our products section!

Here at ClearView, we have a broad range of knowledge and machine vision expertise to help you decide on the right solution for your project.

We offer friendly expertise and a huge range of industry-standard quality machine vision components for printing and packaging, robotics, industrial automation, medicine, life sciences, and the automotive industry, just to name a few.

Our experts are happy to help no matter what your question or problem may be. Feel free to get in touch with us and one of our machine vision experts will be ready to help you get going with your project!

Talk To Us



Machine Vision lets computers read barcodes, data matrix codes, direct part marks, optical character recognition and optical character verification – Learn more about the computer vision technology here

Learn More