Home
Resource
Estimation of salad bar vegetable plate waste in a middle school setting using a digital image recognition model
PDF
PDF format is widely accepted and good for printing.
Plug-in required
PDF-1(1.94 MB)
Citation & Export
View Usage Statistics
Staff View

Citation & Export
Hide

Simple citation

Sampat, Urmi. Estimation of salad bar vegetable plate waste in a middle school setting using a digital image recognition model. Retrieved from https://doi.org/doi:10.7282/t3-dzc0-va69

Export

Click here for information about Citation Management Tools at Rutgers.

Statistics
Hide

Description

TitleEstimation of salad bar vegetable plate waste in a middle school setting using a digital image recognition model
NameSampat, Urmi (author); Tepper, Beverly (chair); Karwe, Mukund (internal member); Takhistov, Paul (internal member); Rutgers University; School of Graduate Studies
Date Created2019
Other Date2019-10 (degree)
SubjectFood Science, Plate Waste, Food waste -- Measurement
Extent1 online resource (xi, 46 pages) : illustrations
DescriptionBackground: The school lunch environment is a prime target for increasing a child’s consumption of fresh fruits and vegetables. Schools are using smarter lunchroom strategies to facilitate healthy choices. However, there is an increasing concern about food waste, especially at school food services. Plate waste at school lunch is used to assess menu performance and meals acceptance using a variety of methodologies. The gold standard for measuring plate waste is the weighing method which is time consuming and costly. This has led researchers to search for alternatives.
Objective: The study aims to test the feasibility and validate the accuracy of a digital image recognition model as a tool to quantify aggregate vegetable waste and compare it against the gold standard “weighing method” in a middle school.
Design: The study was divided in two phases. In phase I, images and weights of the salad plate pre and post consumption were recorded. The model was trained using these data to test the feasibility of model for predicting food classes and estimating physical weights of food. In Phase II, digital images and weights of the salad plates pre and post consumption were recorded and run through the trained model. Aggregate vegetable waste was calculated as the difference between the recorded weights, and the predicted weights assessed through the model.
Results: In Phase I, the image recognition model achieved overall classification accuracy of 85.7% of predicting nine food classes. The mean rank for recorded pre weight was (1.61 g + 0.43 g) and predicted pre weight was (1.01 g + 0.99 g) The feasibility results suggested that there was a significant difference between the recorded and predicted weights (p=0.009). In Phase II, the mean rank for recorded pre weight was (1.63 g + 0.45 g) and predicted weight was (1.73 g + 0.22 g) and did not elicit a statistically significant difference as compared to manually recorded weight (p = 0.341). The mean rank for recorded post weight was (0.62 g + 0.77 g) and weight predicted by the image recognition model was (0.63 g+ 0.80 g) with no statistically significant difference between the two (p=0.619). The mean rank for recorded plate waste was (0.68 % + 0.83%) and plate waste determined by the predicted weights by the image recognition model was (0.72 % + 0.91%). The Wilcoxon signed-rank test showed no statistically significant difference (p=0.177) in plate waste calculated using two methods.
Conclusion: The main findings from this study were that the image recognition model was feasible and accurate for identifying food classes and quantifying vegetable plate waste in a self-serve salad bar in a middle school and did not differ significantly from the gold standard weighing method. This study supports the use
of a digital image recognition model as a valid tool to semi automate data collection and estimate food waste.
NoteM.S.
NoteIncludes bibliographical references
Genretheses, ETD graduate
Persistent URLhttps://doi.org/doi:10.7282/t3-dzc0-va69
LanguageEnglish
CollectionSchool of Graduate Studies Electronic Theses and Dissertations
Organization NameRutgers, The State University of New Jersey
RightsThe author owns the copyright to this work.
Version 8.5.1
Rutgers University Libraries - Copyright ©2023