Limits...
Spectral and Image Integrated Analysis of Hyperspectral Data for Waxy Corn Seed Variety Classification.

Yang X, Hong H, You Z, Cheng F - Sensors (Basel) (2015)

Bottom Line: To reduce the dimension of spectral data, the spectral feature vectors were constructed using the successive projections algorithm (SPA).The results demonstrate that combining spectral and appearance characteristic could obtain better classification results.This procedure has the potential for use as a new method for seed purity testing.

View Article: PubMed Central - PubMed

Affiliation: College of Biosystems Engineering and Food Science, Zhejiang University, 866 Yuhangtang Road, Hangzhou 310058, China. feeling998@126.com.

ABSTRACT
The purity of waxy corn seed is a very important index of seed quality. A novel procedure for the classification of corn seed varieties was developed based on the combined spectral, morphological, and texture features extracted from visible and near-infrared (VIS/NIR) hyperspectral images. For the purpose of exploration and comparison, images of both sides of corn kernels (150 kernels of each variety) were captured and analyzed. The raw spectra were preprocessed with Savitzky-Golay (SG) smoothing and derivation. To reduce the dimension of spectral data, the spectral feature vectors were constructed using the successive projections algorithm (SPA). Five morphological features (area, circularity, aspect ratio, roundness, and solidity) and eight texture features (energy, contrast, correlation, entropy, and their standard deviations) were extracted as appearance character from every corn kernel. Support vector machines (SVM) and a partial least squares-discriminant analysis (PLS-DA) model were employed to build the classification models for seed varieties classification based on different groups of features. The results demonstrate that combining spectral and appearance characteristic could obtain better classification results. The recognition accuracy achieved in the SVM model (98.2% and 96.3% for germ side and endosperm side, respectively) was more satisfactory than in the PLS-DA model. This procedure has the potential for use as a new method for seed purity testing.

No MeSH data available.


Related in: MedlinePlus

The method of hyperspectral image processing, including ROI selection, background segmentation, and feature extraction.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4541845&req=5

sensors-15-15578-f003: The method of hyperspectral image processing, including ROI selection, background segmentation, and feature extraction.

Mentions: The image processing procedure, as illustrated in Figure 3, consisted of a series of steps to acquire data and develop the mathematical model. Initially, every image was calibrated with the dark current and white reference image with Equation (1). Successively, the background was removed according to the contrast of relative reflectance intensity between the black background and kernels. Here 20 × 20 pixels were selected from the kernel and background as a region of interest (ROI). Reflected spectra of the two ROIs were averaged and compared. The results show that the highest variance of wavelength between kernels and background is at about 850 nm. Maize kernels were segmented from the images by a threshold process of image at 850 nm to create a mask of the ROIs. Spectra of each pixel from every kernel were extracted and averaged. Background segmentation and spectra extraction were carried out using ENVI 4.8 (ITT Visual Information Solutions, Boulder, CO, USA).


Spectral and Image Integrated Analysis of Hyperspectral Data for Waxy Corn Seed Variety Classification.

Yang X, Hong H, You Z, Cheng F - Sensors (Basel) (2015)

The method of hyperspectral image processing, including ROI selection, background segmentation, and feature extraction.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4541845&req=5

sensors-15-15578-f003: The method of hyperspectral image processing, including ROI selection, background segmentation, and feature extraction.
Mentions: The image processing procedure, as illustrated in Figure 3, consisted of a series of steps to acquire data and develop the mathematical model. Initially, every image was calibrated with the dark current and white reference image with Equation (1). Successively, the background was removed according to the contrast of relative reflectance intensity between the black background and kernels. Here 20 × 20 pixels were selected from the kernel and background as a region of interest (ROI). Reflected spectra of the two ROIs were averaged and compared. The results show that the highest variance of wavelength between kernels and background is at about 850 nm. Maize kernels were segmented from the images by a threshold process of image at 850 nm to create a mask of the ROIs. Spectra of each pixel from every kernel were extracted and averaged. Background segmentation and spectra extraction were carried out using ENVI 4.8 (ITT Visual Information Solutions, Boulder, CO, USA).

Bottom Line: To reduce the dimension of spectral data, the spectral feature vectors were constructed using the successive projections algorithm (SPA).The results demonstrate that combining spectral and appearance characteristic could obtain better classification results.This procedure has the potential for use as a new method for seed purity testing.

View Article: PubMed Central - PubMed

Affiliation: College of Biosystems Engineering and Food Science, Zhejiang University, 866 Yuhangtang Road, Hangzhou 310058, China. feeling998@126.com.

ABSTRACT
The purity of waxy corn seed is a very important index of seed quality. A novel procedure for the classification of corn seed varieties was developed based on the combined spectral, morphological, and texture features extracted from visible and near-infrared (VIS/NIR) hyperspectral images. For the purpose of exploration and comparison, images of both sides of corn kernels (150 kernels of each variety) were captured and analyzed. The raw spectra were preprocessed with Savitzky-Golay (SG) smoothing and derivation. To reduce the dimension of spectral data, the spectral feature vectors were constructed using the successive projections algorithm (SPA). Five morphological features (area, circularity, aspect ratio, roundness, and solidity) and eight texture features (energy, contrast, correlation, entropy, and their standard deviations) were extracted as appearance character from every corn kernel. Support vector machines (SVM) and a partial least squares-discriminant analysis (PLS-DA) model were employed to build the classification models for seed varieties classification based on different groups of features. The results demonstrate that combining spectral and appearance characteristic could obtain better classification results. The recognition accuracy achieved in the SVM model (98.2% and 96.3% for germ side and endosperm side, respectively) was more satisfactory than in the PLS-DA model. This procedure has the potential for use as a new method for seed purity testing.

No MeSH data available.


Related in: MedlinePlus