Optical Sensing Solutions for Food Sorting

Fast, Reliable Technology for Sorting and Grading of Fruits, Grains and Vegetables

Food sorting and grading are key food manufacturing processes where optical sensing solutions help to ensure consistent quality and improve process efficiency.

 

 

  • Partner with Ocean Optics to create your unique optical sorting solution

  • See what’s happening both outside and inside your sample

  • Enjoy faster, more accurate results than with visual inspection alone

Traditionally, food sorting has been managed using visual inspection, although the introduction of optical scanning has added a more sophisticated level of analysis, with some instruments able to penetrate the peel, skin or shell non-destructively to determine parameters including bruising, rot, fat content, sugar values and moisture levels.

 

Ocean Optics fuses the power of spectroscopy with advanced statistical models and machine learning architecture to achieve smarter and more efficient systems than manual inspection, and ultimately to meet the high quality expectations of consumers.

 

CONTACT US

 

What We Offer

Ocean Optics has a large selection of optical sensing products to match your precise food sorting needs. We’ve been in the miniature spectrometer business for nearly three decades and have developed an extensive array of spectrometers, imaging options and accessories across the UV, Visible and NIR-MIR wavelengths.

 

Many companies need an expert partner to help develop the unique optical sorting models that identify bad samples and distinguish lesser grade from higher quality products. Our team of optical sensing experts including application scientists, spectroscopists and machine learning specialists will help you create an optical sorting solution to meet your exact needs.

 

Whether determining moisture content in dates, sugar levels in oranges, bruises or rot inside pears, or color binning of apples, Ocean can work with you to develop sorting solutions that are faster, more accurate and more reliable than traditional sorting technologies.

Sensing Tools
Capabilities
Insight
 

  • Miniature Spectrometers
  • Multispectral Sensors 
  • Light Sources
  • Sampling Accessories
  • Engineering Services
  • Lab Services
  • Partnership
  • Product Integration
  • Advanced Data Analytics
  • Application Expertise
  • Development of Sorting Algorithm Models
  • Machine Learning

CONTACT US

 

Advantages of Optical Sensing

Optical sensing technologies including spectroscopy and multispectral imaging offer significant advantages compared with traditional sorting approaches such as visual inspection:

  • Enjoy significantly faster and more accurate sorting than with visual inspection
  • More reliably and rapidly sort and grade products by category and quality
  • Ensure more consistent quality measurements than with visual inspection
  • Make non-destructive, non-contact measurements at the surface of, and inside the sample
  • Reduce waste via improved process efficiency
  • Perform multiple sorting tasks at one location
  • Integrate onsite machine learning into process lines

Solutions in Action

 

Case Study: Date Sorting Using Automated Internal Quality Analysis

 

Challenge: Food processors and sorting machine manufacturers demand fast, accurate, robust and simple optical sensing systems to ensure consistent quality and improve process efficiency

 

Solution: With robust hardware, application insight and advanced data analytics from Ocean Optics, food processors and sorting machine manufacturers are improving the quality of fruit and other foods throughout the food chain

 

Traditionally, food sorting has been managed using visual inspection, although the introduction of spectroscopic scanning has added a more sophisticated level of analysis, with some instruments able to penetrate the fruit peel non-destructively to determine parameters including fat content, sugar values and moisture levels. Also, spectroscopy techniques can be integrated into the process stream to measure more samples, at a faster rate, than with manual inspection.

 

Case Study: Lugo Machinery & Innovation, a leading supplier of fresh produce sorting products, approached Ocean Optics seeking an alternative to their manual method of sorting date fruit by moisture level. Their goals: Automate the sorting process to eliminate all manual inspection, and perform the measurements rapidly and non-destructively. What’s more, the customer timeline was very short, with only four months to develop a solution in time for date season.

 

dates image

 

Feasibility tests were performed on date samples from Lugo, which quickly showed NIR correlations to moisture levels in the fruit, helping to determine the choice of system hardware. This setup was used onsite to analyze a much larger sample set, then used for training data to develop proprietary machine learning algorithms.

 

 

Because Lugo had little experience with spectroscopy, they focused primarily on identifying the typical moisture peak for dates. But based on our experience analyzing other fruits and vegetables, we extended the analytical range to include broader patterned spectral features, which would help us to develop machine learning algorithms. This approach — broadband versus discrete wavelength spectral analysis – yields more accurate results and makes the data less susceptible to deviations related to optical interference.

 

The date-sorting system was integrated into a conveyor-belt setup with algorithms running on a devoted PC. The data fed a programmable logic controller (PLC) that triggers a valve, sorting the dates according to moisture level. This beta platform was used to refine and optimize the algorithms before final implementation.

 

Today, the fully integrated system scans 5 dates per second and is entirely automated. This has reduced overhead costs, improved safety and allowed Lugo to focus on refining other aspects of the sorting process. Also, with advanced statistical models now established, Lugo will be able to develop additional analyses without the need for modeling expertise.

 

With the fusion of spectroscopy, statistical modelling and machine learning architecture, sorting machine integrators and food processors can build more efficient sorting and grading systems.

 

CONTACT US

Case Study: Reflectance Spectroscopy Ensures Quality in Apple Sorting

 

Challenge: Undetected browning, spots, blemishes and other flaws can affect fruit quality, damage brand reputation and result in lost business

 

Solution: Optical sensing techniques like UV-Vis spectroscopy are among the tools available to fruit and vegetable packers in assessing quality parameters such as internal and surface color, sugar content and acid level

 

One of the advantages of optical sensing is its versatility, with rapid, non-destructive measurements possible at the surface of the fruit or under the skin or peel, and systems deployable in-line, at-line or in the lab. In addition, sensing tools like spectrometers can be integrated into food sorting machines at the component or sub-assembly level, or used as turnkey systems and combined with advanced data analytics to create powerful measurement capabilities.

 

Case Study: Since 2010, Ocean Optics has worked with a leading European supplier of fruit and vegetable sorting solutions on a system that sorts apples using reflectance spectroscopy. By measuring the apples and then applying chemometric modeling to the results, the sorting supplier can predict fruit quality characteristics including internal browning, which consumers associate with poor quality; and acid level, which is relevant for fruits used in soft drinks.

 

Along the way, technical challenges were tackled as a partnership of Ocean Optics and our customer. These challenges included the speed of the sorting line, which is why a spectrometer with rapid scanning capabilities was selected; the need for a special optical setup to illuminate the samples, which was integrated with our collimating lens to view the reflected light; and the use of chemometrics methods to predict apple parameters such as sugar level, internal browning and acid level.

 

Reflection spectroscopy has the benefit of being non-contact and noninvasive, and can be configured for various samples. When combined with chemometrics modeling, reflection spectroscopy is a powerful tool for extracting information about chemical composition that would otherwise require laboratory analysis. It can be used to address a range of issues related to food quality and safety and can be applied at all points in the supply chain, from producer to consumer.