For Abstracts

Irwin R. Donis-González (Department of Biosystems and Agricultural Engineering, 524 S. Shaw Ln., Michigan State UniversityEast Lansing, MI, 48824. USA)Daniel E. Guyer (Department of Biosystems and Agricultural Engineering, 524 S. Shaw Ln., Michigan State UniversityEast Lansing, MI, 48824. USA)

This research was designed to develop and test an automatic image analysis algorithm to detect the presence of undesirable fibrous tissue before dicing carrots (Daucus carota L.). Fibrous carrot dices are difficult to detect, and are highly problematic when found in ready-to-eat infant food, where they might represent a choking-hazard (safety-concern). A visible/near-infrared (VIS/NIR) hyperspectral imaging (400-1000 nm) system was used to obtain a set of 520-images per sample, from 1233 sections (samples). Samples were collected during the 2013 and 2014 harvesting seasons. Classification accuracy was evaluated by comparing the classes obtained using VIS/NIR hyperspectral images obtained per carrot section to their undesirable fibrous tissue class, based on the industry-simulated invasive quality assessment (% of fiber). Class-0 represents fibrous-free samples, and class-1 denotes samples containing fibrous tissue. After VIS/NIR image preprocessing, cropping, selection, and segmentation, 1045 grayscale intensity and textural features were extracted per sample from five selected VIS/NIR images. A 4-fold cross-validation neural-network classifier with a performance accuracy of 82.4 ± 2.5 % was developed using 122 relevant features, which were selected using a sequential forward selection algorithm with the Fisher discriminant objective function. Findings showed that this methodology is an objective, accurate, and reliable tool to determine the presence of undesirable fibrous tissue in processing carrots, and would be applicable to an automated noninvasive inline sorting system.