Dear {Name},

Spring has landed at Videometer with great enthusiasm from our users, partners and colleagues. We’ve been dedicated to provide you with the best solutions for quality control of various products: from seeds and grains to pharmaceuticals.

In this quarter’s newsletter, we delve into the world of commodity grains and the work we do to aid you with enhanced quality and safety in this industry.

Read along to learn more about the Videometer Technology for automated quality control.

Quality Control with the Videometer Open Classification Models

Developed in cooperation with worldwide users, our Open Classification Models identify quality traits in granular product (seeds, grains, pellets, etc.) and classify them digitally. These mathematical models are continuously trained to adhere to quality standards, ensuring reliable and objective analysis of various grain features.

Videometer's Open Classification Models are effective tools for grain quality inspection. By leveraging spectral imaging technology, we provide the grain commodity industry with the tools needed to standardize, document, and enhance quality control processes. Our goal is to ensure that only the correct quality grains reach the market, benefiting producers and consumers alike.

Available models include corn, OSR, malting barley, sunflower, wheat, soybeans, oat, cowpea, rice, faba beans. Additionally, it is possible to develop and customize models, together with Videometer, based on user needs.

Download the Grain Quality Brochure to learn more.

Enhancing Corn Inspection with the VideometerLab

The VideometerLab is revolutionizing corn quality control by offering high throughput multispectral analysis.

One of the key features of the VideometerLab is its ability to classify products based on their features using advanced mathematical models. The Autofeeder option uses a vibrator to evenly distribute grains onto a belt, which then transports them under the VideometerLab for image acquisition and analysis. The process is automated, ensuring accuracy and consistency in results. This automation speeds up the quality inspection process and makes it more efficient. The system is designed to handle large samples quickly, making it an invaluable tool for quality control.

The intuitive interface of the system allows operators to use the instrument with minimal training. The system stores analysis results in various formats, ensuring thorough documentation for further processing.

For corn quality inspection, the system uses machine learning models to classify kernels based on their characteristics. This includes identifying healthy, broken, mold-damaged, insect-damaged kernels, and more. The classification model can be customized based on your needs, adding extra feature classes or weight densities.

The VideometerLab enhances corn quality control by combining automation, speed, and ease of use, making it an essential tool for improving quality inspection processes.

Differentiating Between Asian and African Rice

Among the VideometerLab users is the Rice Biodiversity Center for Africa (RBCA). The center aims at increasing biodiversity by managing rice genetic resources in Africa. The center raises awareness of the importance of ensuring food and nutrition security by safeguarding rice diversity.

Researchers at RBCA utilize the capabilities of the VideometerLab technology to conduct in-depth phenotyping of rice seeds. The system facilitates the automated characterization of rice seeds, focusing on key crop descriptors such as color and length variations. Leveraging the features found on the VideometerLab Software, researchers analyze descriptive statistics of various grains in their digital grain collections.

Among the different studies at the center, one research focuses on discerning the differentiating factors between African rice (Oryza glaberrima) and Asian rice (Oryza sativa). These two predominant species exhibit distinct traits in terms of yield and climate resilience. While African rice demonstrates significant tolerance to the African environment, its yield is relatively modest. On the other hand, Asian rice boasts higher yields but struggles to adapt to the climates of Western and Central Africa. The projected solution involves the development of an interspecific rice seed that combines the strengths of both species, thereby enabling African farmers to cultivate more resilient crops with enhanced yields.

The Videometer technology is used to comprehensively study the differences between these crops. The rice model allows the utilization of spectral imaging to gather spectral indices of variation between these species. By differentiating African and Asian rice, RBCA moves closer to the research objective—developing an interspecific seed, thus ensuring further food security in Africa.

If you're curious to learn all about Videometer's commodity grain applications, visit our website.

Videometer Webinars Spring 2025

We are thrilled to announce the return of the Videometer Webinar Series for the fourth consecutive year!

This series is designed for anyone interested in exploring the powerful capabilities of the VideometerLab Software. Whether you're new to the platform or looking to deepen your understanding, our webinars offer a comprehensive introduction to the various tools and workflows within VideometerLab.

The webinars cover a range of topics, including spectral image acquisition, machine learning for spectral images, applications of spectral imaging for food and agricultural integrity, advanced transformation building, segmentation building, session recipe building, multispectral fluorescence imaging, and an introduction to the Classifier Design Tool (CDT).

Sign up for the webinars here: