Rapid, Non-Contact Measurement
USING THE MV.C NIR® WITH THE PERCLASS MIRA® SCANNING STAGE
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 industrial machine vision systems 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.
Overview
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.
BENEFITS OF HYPERSPECTRAL IMAGING
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.
______________