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

Selected variables using SPA, spectra extracted from germ-up (a) and germ down (b) images.
© Copyright Policy
Related In: Results  -  Collection

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

sensors-15-15578-f006: Selected variables using SPA, spectra extracted from germ-up (a) and germ down (b) images.

Mentions: As described above, the raw spectral data were preprocessed by SG smoothing and derivation. After this, the optimal wavelength spectra were selected by SPA. SPA was proposed as a novel method to minimize variable collinearity and select the optimal variable [31]. This algorithm started with one wavelength, and then added a new one in each iteration process, and a specified number of wavelengths were selected at the end. The selections of optimal wavebands are shown in Figure 6 and Table 1. The results of wavelength selection are related to the image type from which the spectra information was extracted. The most optimal wavebands of germ-up images concentrated in the regions of lower wavelength (<500 nm) and higher wavelength (800–940 nm), as the most optimal wavebands of germ-down images were located in the region of 500–650 nm. In terms of composition, the germ side contains starch, oil (in the embryo), and other chemical compounds. The leading composition is starch in the endosperm side. Accordingly, the oil- and starch-related bands were reflected in the optimal wavebands, respectively.


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)

Selected variables using SPA, spectra extracted from germ-up (a) and germ down (b) images.
© Copyright Policy
Related In: Results  -  Collection

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

sensors-15-15578-f006: Selected variables using SPA, spectra extracted from germ-up (a) and germ down (b) images.
Mentions: As described above, the raw spectral data were preprocessed by SG smoothing and derivation. After this, the optimal wavelength spectra were selected by SPA. SPA was proposed as a novel method to minimize variable collinearity and select the optimal variable [31]. This algorithm started with one wavelength, and then added a new one in each iteration process, and a specified number of wavelengths were selected at the end. The selections of optimal wavebands are shown in Figure 6 and Table 1. The results of wavelength selection are related to the image type from which the spectra information was extracted. The most optimal wavebands of germ-up images concentrated in the regions of lower wavelength (<500 nm) and higher wavelength (800–940 nm), as the most optimal wavebands of germ-down images were located in the region of 500–650 nm. In terms of composition, the germ side contains starch, oil (in the embryo), and other chemical compounds. The leading composition is starch in the endosperm side. Accordingly, the oil- and starch-related bands were reflected in the optimal wavebands, respectively.

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