Page Banner

United States Department of Agriculture

Agricultural Research Service

Research Project: TECHNOLOGIES FOR QUALITY MEASUREMENT AND GRADING OF FRUITS AND VEGETABLES

Location: Sugarbeet and Bean Research

Title: Integrated spectral and image analysis of hyperspectral scattering data for prediction of apple fruit firmness and soluble solids content

Authors
item Mendoza, Fernando
item Lu, Renfu
item Ariana, Diwan -
item Cen, Haiyan -
item Bailey, Benjamin

Submitted to: Postharvest Biology and Technology
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: May 28, 2011
Publication Date: November 1, 2011
Citation: Mendoza, F., Lu, R., Ariana, D., Cen, H., Bailey, B.B. 2011. Integrated spectral and image analysis of hyperspectral scattering data for prediction of apple fruit firmness and soluble solids content. Postharvest Biology and Technology. 62(2):149-160.

Interpretive Summary: Firmness and soluble solids content (SSC) are critical quality attributes for fresh apple fruit because they directly influence the consumer purchasing decision. Researchers have explored different methods (i.e., mechanical, sonic, optical and electrical) for nondestructive evaluation of these quality attributes. Among them is hyperspectral scattering technique, which measures spectral reflectance profiles from an object in a spatial resolved manner for contiguous wavelengths, and it has demonstrated great potential for assessing fruit firmness and SSC. However, previous mathematical models for describing the spectral scattering features are based on the analysis of individual or averaged spectral scattering profiles in the spectral dimension only, and they did not consider the pixel intensity distribution (also known as organization or intensity pattern) from the overall 2-D scattering images. The main purpose of this research was thus to improve the prediction of firmness and SSC for 'Golden Delicious' (GD), 'Jonagold' (JG), and 'Red Delicious' (RD) apples by integration of critical information extracted from the hyperspectral scattering images based on 1-D scattering profiles and 2-D image analysis techniques. To better assess the performance of the proposed mathematical approach, apples from two harvest seasons were imaged over the wavelength region of 500-1,000 nm using two different hyperspectral imaging setups: a stationary system for GD in 2006 and a prototype on-line system for JG and RD in 2009. Compared with the spectral scattering profile analysis method developed in previous studies, the integrated method has improved firmness prediction by 7-16% and SSC prediction by 3-11% for the three cultivars of apple. This new approach of analyzing hyperspectral scattering data would enable spectral scattering technique to better meet the requirement for online sorting and grading of apples for firmness and SSC.

Technical Abstract: Spectral scattering is useful for assessing the firmness and soluble solids content (SSC) of apples. In previous research, mean reflectance extracted from the hyperspectral scattering profiles was used for this purpose since the method is simple and fast and also gives relatively good predictions. The objective of this study was to improve firmness and SSC prediction for 'Golden Delicious' (GD), 'Jonagold' (JG), and 'Red Delicious' (RD) apples by integration of critical spectral and image features extracted from the hyperspectral scattering images over the wavelength region of 500-1,000 nm, using spectral scattering profile and image analysis techniques. Scattering profile analysis was based on mean reflectance method and discrete and continuous wavelet transform decomposition, while image analysis included textural features based on first order statistics, Fourier analysis, co-occurrence matrix and variogram analysis, as well as multi-resolution image features obtained from discrete and continuous wavelet analysis. A total of 294 parameters were extracted by these methods from each apple, which were then selected and combined for predicting fruit firmness and SSC using partial least squares (PLS) method. Prediction models integrating spectral scattering and image characteristics have improved firmness and SSC prediction results compared with the mean reflectance method when used alone. The standard errors of prediction (SEP) for GD, JG, and RD apples were reduced by 6.6, 16.1, 13.7% for firmness (R-values of 0.87, 0.95, and 0.84 and the SEPs of 5.9, 7.1, and 8.7 N), and by 11.2, 2.8, and 3.0% for SSC (R-values of 0.88, 0.78, and 0.66 and the SEPs of 0.7, 0.7,and 0.9 Brix), respectively.

Last Modified: 10/26/2014
Footer Content Back to Top of Page