Spectroscopy Since 1975
Metrohm Advertisement

Headwall acquires perClass

8 July 2022 | News
by Ian Michael

Headwall Photonics has acquired perClass BV, the developer of the perClass Mira® spectral analysis software package, which integrates with various spectral sensors and enables intuitive spectral imaging analysis for advanced machine vision applications in research, industrial and various commercial deployments.

“Spectral imaging has been used in research for decades to help answer a variety of complex questions. Until recently, this involved a time-consuming process of data acquisition, model development, and lengthy data analysis typically performed by a senior level scientist”, noted Don Battistoni, President of Headwall. “perClass Mira eliminates those complexities through an intuitive interface backed up by advanced machine learning algorithms, in the process dramatically expanding the addressable use cases for spectral imaging across numerous industrial markets.”

“The perClass mission remains to simplify interpretation of spectral imaging data to expand deployment for industrial applications”, Dr Pavel Paclik, perClass Founder and General Manager adds. “We remain dedicated to and will continue to support and work with our many loyal and new spectral sensor manufacturer partners. This growth investment and our extended partnership with Headwall will facilitate our ability to provide best-in-class solutions to the market for any sensor, and our deeper integration with a leading sensor provider accelerates our goal of advancing widespread adoption of spectral imaging in real-world applications.”

Headwall’s Hyperspec® MV.X already utilises perClass Mira to both create spectral classification models and deploy them in applications such as the detection of food contamination, material sorting in recycling, and grading of fruit and nuts, amongst other applications. Both Headwall and perClass are focused on bringing hyperspectral imaging to more industries and researchers globally by introducing more intuitive yet powerful spectral analysis workflows and by eliminating the data interpretation complexities that have historically limited broader hyperspectral imaging adoption.

Rate this Article
No votes yet