Modifying machine vision for produce inspection.
Through a formal agreement with South Korea's Rural Development Administration, USDA-ARS scientists are collaborating on applications for this technology for use in South Korea. For the past several years, scientists have been optimizing the sensing technology for use on fresh produce.
The researchers have developed and patented a multitask imaging system capable of examining the quality and safety attributes of apples. The technology scans three to four apples per second, providing efficient and effective inspection of defects and fecal contamination. The scientists are looking at ways to improve the technology, such as developing methods to examine the entire surface of a round object.
These machine vision systems use optoelectronics and sensors to visualize an object, in this case, food. At the heart of these systems is a digital multispectral camera that can image objects at different wavelengths of light simultaneously and can even detect light invisible to the naked eye. These systems rely on two or three wavelengths of light that have been selected to do the best job of visualizing certain features.
The purpose of machine vision is to supplement human inspectors with instruments that image every single fruit, vegetable, meat or poultry product as it speeds by on the processing line. Typical lines today can process about 360 pieces of fruit per minute or up to 180 poultry carcasses per minute.
Machine vision can be used to detect almost all biological conditions that cause inspectors to re-examine chicken carcasses, such as signs of disease that pose food safety risks or otherwise mar a chicken's consumer appeal. Previously, ARS scientists developed a spectral line-scan imaging system for the automated online wholesomeness inspection of broilers. The system was evaluated in a commercial chicken processing plant.
Further information. Moon Kim, USDA-ARS Environmental Microbial and Food Safety Laboratory, 10300 Baltimore Ave., Beltsville, MD 20705; phone: 301-504-8450; email: email@example.com.
|Printer friendly Cite/link Email Feedback|
|Publication:||Emerging Food R&D Report|
|Date:||Apr 1, 2012|
|Previous Article:||Use filtration technology to produce functional beta-casein.|
|Next Article:||Color test enhances tomato analyzer software.|