Perfect Recipe: In-line Hyperspectral Imaging System Controls Cookie Quality
Industrial vision system relies on Kowa optics to measure fat content of cookies and pastries on the production line
Hyperspectral imaging can be seen as a paradigm shift in vision systems and as a source of abundant, high-quality data to feed vision systems based on artificial intelligence algorithms. Instead of the usual three-color channels in artificial vision, hyperspectral imaging uses up to hundreds of channels. This makes it possible to see very subtle differences. Besides that, hyperspectral cameras often have an extended spectral range beyond the visible, i.e. into the infrared spectrum. As a result, hyperspectral imaging makes it possible to determine chemical and physical properties of a product, for example to sort plastics in a recycling facility or to inspect the quality of organic products in the food industry.
Until now, however, the use of this technology has been limited to very specific environments: military applications and research laboratories. IRIS Technology, a Spanish engineering company has developed solutions to implement hyperspectral imaging for in-line industrial inspection. This includes both appropriate hardware and machine learning algorithms tailored to each application.
One good example for a successful implementation of hyperspectral imaging in an industrial application is the solution developed by IRIS for a major industrial bakery to determine, in real time and continuously, the fat content of cookies and pastries.
Unexplained changes in product properties
In the food industry, it is essential to keep the manufacturing process under control to ensure that the quality and taste of the product remains constant for a given recipe. Controlling the fat content is particularly essential. It is critical to manage and maintain a precise level of the raw material – in this case oil. This is demanded not only by consumption trends, but also because large variations in the fat value result in cost overruns. When the fat value input is well above or below the optimal value it can lead to unexpected changes in the palatability of the product.
IRIS’ customer, a leading food company specialized in cookies and pastries, observed changes in the product that could hardly be explained by formulation changes. Therefore, a study was started to see which processes were producing these changes. The study was slow and complicated because current laboratory techniques to control the fat value are off-line, and require specific sampling, preparation, inputs and personnel. Results take several hours to be delivered and it is never possible to notice these variations and rectify the process in real time. This makes such methods incompatible with the idea of standardizing the product, the use of raw materials and particularly with any attempt to optimize the critical quality parameters in the production process.
In-line measurement for immediate correction
What the factory needed was a continuous measurement – and information – at a minimum margin of error to quickly measure the fat content to be able to relate it to changes in his processes. The company turned to IRIS to implement an in-line hyperspectral imaging solution that performs a 100% inspection of the products and determines their fat content in real time. The system is based on the IRIS VISUM HSI hardware platform. VISUM HSI is an industrial in-line HyperSpectral Imaging analyzer that can be integrated into any type of production line for real-time monitoring of product quality when the spatial information (shape and position) is relevant, extending artificial vision to full chemical sight unit by unit.
VISUM HSI relies on a line scan camera with short wave infrared (SWIR) sensitivity (900-1,700 nanometer). This makes it well suited to measure fat content, which can be best identified at 1,200 nm and around 1,750 nm. The system can capture up to 300 lines per second to inspect the products without slowing down the process. IRIS Technology Solutions’ integrated software and chemometrics tools enable the user to self-calibrate the device to changes in product composition and it is seamlessly interfaced with plant information systems.
Crisp images with Kowa SWIR-optimized lenses
One specific challenge of SWIR imaging is the choice of the right optics. Lenses designed for the visible spectrum are not suitable for hyperspectral imaging. Infrared light does not focus like visible light, which results in blurry images. “We have tested several lens types from various manufacturers”, explains Joan Puig, Deputy Director at IRIS. “We finally settled for Kowa’s LM8HC-SW because of its outstanding performance over the full spectral range of our VISUM HIS system”.
The Kowa LM8HC-SW is an 8mm industrial lens for optimized for the short wave infrared spectrum (SWIR), which make it ideal for the detection of fat at 1,200 and 1,750 nm. It is part of the Kowa HC-SW series of SWIR-optimized lenses that also includes models with 12.5mm, 16mm, 25mm, 35mm and 50mm focal length to fit any application. Kowa’s industrial-grade design was also a good fit to the VISUM HIS’ rugged hardware optimized for harsh environments.
The VISUM HIS inspection system has been in operation successfully for more than half a year on the bakery’s production line. Thanks to this system, the bakery was able to identify the process issue that caused variations in fat content in the fermentation process and took corrective action. As a result, fat content has been stabilized and the oil consumption of the manufacturing process was reduced by 1.5%. With this the right hardware, optical components and software, the company can permanently monitor the fat content of their products to ensure both a constant product quality and optimized manufacturing costs with no oil waste. Any parameter drift automatically generates an alarm so corrective actions can be taken immediately. The success of this project convinced the IRIS’ customer to implement the system at other manufacturing sites.
Ideal solution for food inspection
What is true for fat is also true for other parameters in food manufacturing, such as moisture, fat, sugars, seasonings, or others. There is an “optimal” value in the quality vs. production costs equation, but it is difficult to achieve due to the lack of real time measurement and information of the chemical composition of the product. IRIS Technology’s hyperspectral imaging systems, coupled with Kowa’s SWIR-optimized industrial lenses, make it possible for food manufacturers to monitor the conformity of their products to the recipe in real time without slowing down the production process.
Hyperspectral imaging can be seen as a paradigm shift in vision systems and as a source of abundant, high-quality data to feed vision systems based on artificial intelligence algorithms. Instead of the usual three-color channels in artificial vision, hyperspectral imaging uses up to hundreds of channels. This makes it possible to see very subtle differences. Besides that, hyperspectral cameras often have an extended spectral range beyond the visible, i.e. into the infrared spectrum. As a result, hyperspectral imaging makes it possible to determine chemical and physical properties of a product, for example to sort plastics in a recycling facility or to inspect the quality of organic products in the food industry.
Until now, however, the use of this technology has been limited to very specific environments: military applications and research laboratories. IRIS Technology, a Spanish engineering company has developed solutions to implement hyperspectral imaging for in-line industrial inspection. This includes both appropriate hardware and machine learning algorithms tailored to each application.
One good example for a successful implementation of hyperspectral imaging in an industrial application is the solution developed by IRIS for a major industrial bakery to determine, in real time and continuously, the fat content of cookies and pastries.
Unexplained changes in product properties
In the food industry, it is essential to keep the manufacturing process under control to ensure that the quality and taste of the product remains constant for a given recipe. Controlling the fat content is particularly essential. It is critical to manage and maintain a precise level of the raw material – in this case oil. This is demanded not only by consumption trends, but also because large variations in the fat value result in cost overruns. When the fat value input is well above or below the optimal value it can lead to unexpected changes in the palatability of the product.
IRIS’ customer, a leading food company specialized in cookies and pastries, observed changes in the product that could hardly be explained by formulation changes. Therefore, a study was started to see which processes were producing these changes. The study was slow and complicated because current laboratory techniques to control the fat value are off-line, and require specific sampling, preparation, inputs and personnel. Results take several hours to be delivered and it is never possible to notice these variations and rectify the process in real time. This makes such methods incompatible with the idea of standardizing the product, the use of raw materials and particularly with any attempt to optimize the critical quality parameters in the production process.
In-line measurement for immediate correction
What the factory needed was a continuous measurement – and information – at a minimum margin of error to quickly measure the fat content to be able to relate it to changes in his processes. The company turned to IRIS to implement an in-line hyperspectral imaging solution that performs a 100% inspection of the products and determines their fat content in real time. The system is based on the IRIS VISUM HSI hardware platform. VISUM HSI is an industrial in-line HyperSpectral Imaging analyzer that can be integrated into any type of production line for real-time monitoring of product quality when the spatial information (shape and position) is relevant, extending artificial vision to full chemical sight unit by unit.
VISUM HSI relies on a line scan camera with short wave infrared (SWIR) sensitivity (900-1,700 nanometer). This makes it well suited to measure fat content, which can be best identified at 1,200 nm and around 1,750 nm. The system can capture up to 300 lines per second to inspect the products without slowing down the process. IRIS Technology Solutions’ integrated software and chemometrics tools enable the user to self-calibrate the device to changes in product composition and it is seamlessly interfaced with plant information systems.
Crisp images with Kowa SWIR-optimized lenses
One specific challenge of SWIR imaging is the choice of the right optics. Lenses designed for the visible spectrum are not suitable for hyperspectral imaging. Infrared light does not focus like visible light, which results in blurry images. “We have tested several lens types from various manufacturers”, explains Joan Puig, Deputy Director at IRIS. “We finally settled for Kowa’s LM8HC-SW because of its outstanding performance over the full spectral range of our VISUM HIS system”.
The Kowa LM8HC-SW is an 8mm industrial lens for optimized for the short wave infrared spectrum (SWIR), which make it ideal for the detection of fat at 1,200 and 1,750 nm. It is part of the Kowa HC-SW series of SWIR-optimized lenses that also includes models with 12.5mm, 16mm, 25mm, 35mm and 50mm focal length to fit any application. Kowa’s industrial-grade design was also a good fit to the VISUM HIS’ rugged hardware optimized for harsh environments.
The VISUM HIS inspection system has been in operation successfully for more than half a year on the bakery’s production line. Thanks to this system, the bakery was able to identify the process issue that caused variations in fat content in the fermentation process and took corrective action. As a result, fat content has been stabilized and the oil consumption of the manufacturing process was reduced by 1.5%. With this the right hardware, optical components and software, the company can permanently monitor the fat content of their products to ensure both a constant product quality and optimized manufacturing costs with no oil waste. Any parameter drift automatically generates an alarm so corrective actions can be taken immediately. The success of this project convinced the IRIS’ customer to implement the system at other manufacturing sites.
Ideal solution for food inspection
What is true for fat is also true for other parameters in food manufacturing, such as moisture, fat, sugars, seasonings, or others. There is an “optimal” value in the quality vs. production costs equation, but it is difficult to achieve due to the lack of real time measurement and information of the chemical composition of the product. IRIS Technology’s hyperspectral imaging systems, coupled with Kowa’s SWIR-optimized industrial lenses, make it possible for food manufacturers to monitor the conformity of their products to the recipe in real time without slowing down the production process.
Related Posts
0211-542184-0
