PRIMELABS LLC — Department of Agriculture SBIR Phase I: 8.5

Description

Meat is a highly perishable food and requires proper storage processing and packaging. Meatproducts decompose naturally because of high fat and water contents that render them susceptibleto spoilage by both lipid oxidation and microbial contamination. The spoiled meat is hazardous dueto microbial growth and the subsequent transmission of food borne illnesses. Food packaging is oneof the main processes to preserve the quality of food products for transportation storage and enduse. Currently there is a rapidly growing demand by consumers and manufacturers for smart foodquality monitoring solutions to (i) detect sense and record deterioration inside the food packageand (ii) ensure the safety preserve quality and warn about possible problems during food transportand storage. These smart strategies help to increase the food products shelf-life by real-time qualitymonitoring thereby improving the profitability to manufacturers and supermarkets and reducing thecost of food products for consumers.We propose to develop and commercialize a low-cost clip-based add-on system that utilizes theavailable camera in a smartphone to create a high-performance multispectral imager (MSI). Ourproposed add-on utilizes a custom developed 9-position electronic filter wheel with Bluetoothconnectivity that works with our custom image processing application that can be downloaded freeof cost. This smartphone based MSI system can be used with modified atmosphere packaging(MAP) or aerobically packaged meat to provide information about the quality and safety of meatproduct and the proposed technology does not require any modification of the meat packaging. Wedeveloped a neuro-fuzzy approach to provide an intelligent decision support system for thedetection of meat spoilage using multispectral images. The innovation of the proposed approach isfurther extended to the identification of the temperature used for storage along with meat spoilagewhile utilizing only imaging spectral information.