Close this search box.
Close this search box.

Surface Moisture Estimation of Bread: Rapid, Non-Contact Measurement

Rapid, Non-Contact Measurement


Hyperspectral scan of bread moisture content

A significant challenge for industrial production of baked goods is monitoring moisture content. This attribute is a crucial measurement at all stages of production. Raw materials can contain water that can cause clumping or degradation of products during storage, lowering shelf-life and product value.

Moisture content can be determined by vacuum or convention ovens. However, those methods can only sample a small portion of the population of the product,1 and may require heating of the samples, risking degradation of the product. Hyperspectral imaging provides an opportunity to estimate the moisture content without the risk of degradation. Headwall’s hyperspectral imagers paired with perClass Mira® analysis software, provide a non-contact estimation of this critical component in minutes, either inline or offline using the perClass Mira Scanning Stage.


In a recent study, water was applied to the surface of different slices of bread. Scans of the bread were taken using perClass Mira Software and with Headwall’s MV.C NIR hyperspectral imaging sensor on the perClass Mira Stage. This process was repeated over the course of an hour as the water evaporated. From these scans, a regression model was created to estimate the water content of the bread.


Regression Modeling

Using the hyperspectral imaging scans, a perClass Mira classification model was trained to distinguish between the background and the slice of bread, and the slice of bread segmented out as an object. This object was then assigned a value from 0 to 60, noting how many minutes have passed since the water was applied. The perClass Mira software then created a regression model using the mean spectra of the bread, and predicted the surface moisture content of the other pieces of bread. In addition to moisture content estimation, circularity and size of the baked goods can also be determined via perClass Mira software and exported downstream for inline action.



The results of this study show that perClass Mira has the capability to determine surface moisture content without heating and potentially altering the product. Hyperspectral images can be scanned and analyzed in real time, offering faster information about the product and potentially 100% product inspection to ensure quality. Headwall’s MV.C NIR combined with perClass Mira Software and Scanning Stage offers a tool for fast and contactless solutions for your industrial baking needs.


The perClass Mira Stage with Headwall MV.C NIR hyperspectral imager, scanning moisture content in bread

Want to know more?

Our Headwall Applications Team will work with you to explore how HSI can deliver value to your fruit processing plant or citrus grove! Spectral Imaging, Food Quality Field boxes or entire truck loads can be scanned in minutes and the results sent to production control stations. Real-time results help speed up receiving operations, optimize decision making and deliver significant ROI.

More Application Notes

An RGB image of a mixture of herbs and spices alongside a hyperspectral false-color scan of the same pile.
Cayenne and Oregano

Spectral classification via the perClass Mira Software makes the task of assessing herb and spice quality less challenging by providing a clear indication of the

Read More »

Explore more content

Hyperspectral 101

Webinar / Videos

Published Research