Sanovo Technology Group has signed a worldwide exclusive license agreement with JigLabs to develop an optical-based, computer vision system, using artificial intelligence to detect cracks.

For many years egg crack detection has been based on acoustical measurements. A signal is generated by the egg hitting sensors or by hammers, creating vibration in the eggshell, transferred to a sensor. This sensor converts the vibration to an electrical signal to identify and reject eggs with defective shells.

Sound-based systems impose mechanical stress on the eggshell, but also increase the risk of cross-contamination among eggs and acoustic detection requires manual cleaning and occasionally dismantling for inspection.

 With increasing food safety concerns, innovative crack detection requires a new solution obviating direct contact between eggs and detectors. Accordingly SANOVO has signed an agreement with JigLabs, a software development company for an optical-based computer vision system that uses deep learning and artificial intelligence to detect cracks and leakers.

Jan Holm Holst, R&D Director at SANOVO stated: “Optical detection of egg cracks, especially hair-line cracks, has been tried for many years and several patents have been granted.  This new and specially designed artificial neural network algorithm, imbedded in advanced, high-performing hardware, represents a revolutionary change to the future of egg crack detection, with the potential for this technology to displace sonic based systems used today.”

Evaluation of the system in a plant in the U.S. packing white eggs confirmed superiority over sound-based crack detection. Advantages included:-

• More stable detection due to the elimination of mechanical moving parts
• Obviating contamination of sensors.
• Almost maintenance-free since the vision system is based on advanced camera technology and LED light sources

Jan-Willem Pennings, R&D Manager at SANOVO opined, “when I was introduced to the concept, I saw all the potential benefits of the system. The crack detection concept is totally non-contact compared to the available sonic systems on the market. This means no potential further damage to the final product. The system requires no extra transfers with grippers or a change in the carrying surface causing damage by transfer of eggs. The system is static without moving parts, resulting in low maintenance and operating cost. No adjustments are required for egg size”.

 To commercialize this innovation for all types of eggs, SANOVO and JigLabs are currently working on system integration and optimization of the technology. SANOVO anticipates revolutionizing crack detection in egg graders all around the world.