Determination of spectral resolutions for multispectral detection of apple bruises using visible/near-infrared hyperspectral reflectance imaging

Authors: Baek, Insuck; MO, CHANGYEUN - Kangwon National University; EGGLETON, CHARLES - University Of Maryland; GADSDEN, STEPHEN - University Of Guelph; CHO, BYOUNG-KWAN - Chungnam National University; LEE, HOONSOO - Chungbuk National University; Kim, Moon; Qin, Jianwei - Tony Qin

Submitted to: Frontiers in Plant Science
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 8/10/2022
Publication Date: 8/29/2022
Citation: Baek, I., Mo, C., Eggleton, C., Gadsden, S.A., Cho, B., Lee, H., Kim, M.S., Qin, J. 2022. Determination of spectral resolutions for multispectral detection of apple bruises using visible/near-infrared hyperspectral reflectance imaging. Frontiers in Plant Science. 13:963591. https://doi.org/10.3389/fpls.2022.963591.
DOI: https://doi.org/10.3389/fpls.2022.963591

Interpretive Summary: Although many have explored important aspects of developing automated imaging systems for nondestructive apple bruise detection (such as identifying effective wavelengths of light and specific imaging processing algorithms), this is not yet a simple task. This study demonstrates a method by which to answer the following questions related to optimizing spectral parameters for effective apple bruise detection by a line-scan hyperspectral imaging system: Which wavebands of visible/near-infrared light to use, how many of those wavebands to use, and with what bandwidth should each waveband be used with? In particular, waveband-specific spectral resolution with selections specific to particular classification methods has not been addressed by previous research. Hyperspectral image data for 144 Golden Delicious apples that were prepared with, low-, medium-, and high-impact bruising were collected in this study and used to select and test key wavebands and their combinations and bandwidths with four image-based classification methods. Each method was found to have a different optimized resolution for high accuracy bruise detection, and the optimized resolutions also allowed for use of shorter exposure times. The results of this work can be used by researchers and industry to develop multispectral imaging systems to provide rapid, cost-effective post-harvest processing to identify bruised apples on commercial processing lines.

Technical Abstract: This study demonstrates a method to select wavelength-specific spectral resolutions to optimize a line-scan hyperspectral imaging method for its intended use, which in this case was visible/near-infrared imaging-based multiple-waveband detection of apple bruises. Many earlier studies have explored important aspects of developing apple bruise detection systems, such as key wavelengths and image processing algorithms. Despite the endeavors of many, development of a real-time bruise detection system is not yet a simple task. To overcome these problems, this study investigated selection of optimal wavelength-specific spectral resolutions for detecting bruises on apples by using hyperspectral line-scan imaging with the Random Track function for non-contiguous partial readout, with two experimental parts. The first part identified key-wavelengths and the optimal number of key-wavelengths to use for detecting low-, medium-, and high-impact bruises on apples. These parameters were determined by principal component analysis (PCA) and sequential forward selection (SFS) with four classification methods. The second part determined the optimal spectral resolution for each of the key-wavelengths by selecting and evaluating twenty-one combinations of exposure time and key-wavelength bandwidths, and then selecting the best combination based on the bruise detection accuracies achieved by each classification method. Each of the four classification methods was found to have a different optimized resolution for high accuracy bruise detection, and the optimized resolutions also allowed for use of shorter exposure times. The results of this work can be used to help develop multispectral imaging systems that provide rapid, cost-effective post-harvest processing to identify bruised apples on commercial processing lines.