AUTHOR=Ding Ling , Hoover Amber N. , Emerson Rachel M. , Lin Kuan-Ting , Gruber Josephine N. , Donohoe Bryon S. , Klinger Jordan L. , Colby Rachel D. , Thomas Brad J. , Smith William A. , Ray Allison E. 

TITLE=Image Analysis for Rapid Assessment and Quality-Based Sorting of Corn Stover

JOURNAL=Frontiers in Energy Research

VOLUME=Volume 10 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/energy-research/articles/10.3389/fenrg.2022.837698

DOI=10.3389/fenrg.2022.837698

ISSN=2296-598X

ABSTRACT=Imaging can be applied to assess quality in many industries. For example, it has been investigated as a tool to distinguish plant growth in response to drought, differences in wood products, and to sort municipal solid waste (MSW). However, the variability of feedstock material and quality attributes in corn stover and its related impact on integrated preprocessing and conversion is complex and not fully understood. Imaging in the visible spectrum is a low-cost tool that can be readily deployed for in-field or over-belt monitoring and subsequent diversion or alternative processing of biomass feedstock by identifying contaminants or other chemical or physical attributes impacting processing and conversion processes. Image analysis was employed in this study to evaluate the quality of corn stover in red-green-blue (RGB) color space. This study used controlled, bench-scale imaging as a proof-of-concept for rapid quality assessment of corn stover based on variations in material attributes, including chemical and physical attributes, that relate to biological degradation and soil contamination. Logistic regression-based classification algorithms were used to develop a method for biomass screening as a function of biological degradation or soil contamination. This study demonstrates the use of image analysis to extract features from red-green-blue (RGB) color space of corn stover images to investigate variations in critical material attributes that range from chemical composition, supported by investigation using FTIR, to more detailed surface analysis. These insights offer promise for development of a rapid screening tool that could be deployed by farmers for in-field assessment of biomass quality or biorefinery operators for in-line sorting and process optimization.