A NOVEL HYPERSPECTRAL LINE-SCAN IMAGING METHOD FOR WHOLE SURFACES OF ROUND-SHAPED AGRICULTURAL PRODUCTS
Loading...
Links to Files
Permanent Link
Author/Creator
Author/Creator ORCID
Date
2019-01-01
Type of Work
Department
Mechanical Engineering
Program
Engineering, Mechanical
Citation of Original Publication
Rights
Distribution Rights granted to UMBC by the author.
Access limited to the UMBC community. Item may possibly be obtained via Interlibrary Loan thorugh a local library, pending author/copyright holder's permission.
This item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.
Access limited to the UMBC community. Item may possibly be obtained via Interlibrary Loan thorugh a local library, pending author/copyright holder's permission.
This item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.
Abstract
The goal of this research was to develop an online whole surface imaging inspection system for round fruit. Many round-shaped fruits have potential consumer safety issues or quality management problems that current real-time hyperspectral line-scanning systems cannot overcome. For example, current systems do not scan the entire surface of round fruits due to a lack of access and technical challenges. Previous attempts at developing online whole surface scanners were not successful due to low image quality, hardware limitations, and high system costs. To overcome these problems, this thesis presents a novel technology that uses line-scan hyperspectral cameras that may be readily used in a commercial setting, such as in a sorting line for food safety and quality control. Three main steps were completed in order to develop the system. First, the key-wavelengths and optimal number of wavelengths were determined for detecting various bruises on apples. These parameters were determined by principal component analysis (PCA) and sequential forward selection (SFS) with classification methods. Next, the optimal resolution of wavelengths was determined based on key-wavelengths. This was accomplished by studying 22 combinations, collecting measurements, and then selecting the best combination based on the accuracy of each classification method. The third step was to develop a method for imaging the whole target surface (e.g., apple). The developed method used auxiliary mirrors and a single line-scan camera for deploying in an online system. This research demonstrates that multispectral imaging systems provide cost-effective post-harvest processing of fresh fruit on a commercial processing line by enabling single-instrument-based whole-surface inspection. The developed system will complement current automated screening and sorting based on quality attributes by the addition of safety inspection. Finally, the developed system enables distributors to provide a high-quality product for the customer while reducing the unit cost of production.