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 hyperspectral imaging system: (1) CCD camera; (2) imaging spectrograph; (3) lens; (4) scattering cylinder; (5) sample stage; (6) electrical moving stage; (7) dark room; (8) light source; (9) light source controller; (10) moving stage controller; (11) computer.
© Copyright Policy
Related In: Results  -  Collection

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

sensors-15-15578-f001: The hyperspectral imaging system: (1) CCD camera; (2) imaging spectrograph; (3) lens; (4) scattering cylinder; (5) sample stage; (6) electrical moving stage; (7) dark room; (8) light source; (9) light source controller; (10) moving stage controller; (11) computer.

Mentions: The customized visible and near-infrared (VIS/NIR) HSI system was applied. The system consisted of an image spectrograph (Imspector V10E-QE, Spectral Imaging Ltd., Oulu, Finland), a digital charge-coupled device (CCD)camera (C8484-05G, Hamamatsu Photonics, Hamamatsu, Japan), a camera lens (V23-f/2.4 030603, Specim Ltd, Oulu, Finland), illumination and a controller, a sample stage and electric moving stage, a dark room, and a computer (Figure 1). The line scanning image spectrograph had a spectral range of 400–1000 nm and maximum image size of 6.15 × 14.2 mm (spectral × spatial). In this study, the compression mode was set as 2 × 2 binning. The CCD camera has a high-resolution of 1344 (H) × 1024 (V), a wide dynamic range of 12-bit digital output, and high sensitivity in the VIS/NIR region. The illumination consisted of a linear light (P/N 9130, Illumination Technologies, Inc., Elbridge, NY, USA) and a light-scattering cylinder to make the light uniform and even. In order to prevent images from being blurred or deformed, the intensity of illumination, the speed of the electric moving stage, the exposure time of the camera, and the object distance were all set at appropriate values. The object distance was set at 420 mm, the speed of the electric moving stage was fixed at 2.8 mm/s, and the exposure time was set at 90 ms.


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 hyperspectral imaging system: (1) CCD camera; (2) imaging spectrograph; (3) lens; (4) scattering cylinder; (5) sample stage; (6) electrical moving stage; (7) dark room; (8) light source; (9) light source controller; (10) moving stage controller; (11) computer.
© Copyright Policy
Related In: Results  -  Collection

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

sensors-15-15578-f001: The hyperspectral imaging system: (1) CCD camera; (2) imaging spectrograph; (3) lens; (4) scattering cylinder; (5) sample stage; (6) electrical moving stage; (7) dark room; (8) light source; (9) light source controller; (10) moving stage controller; (11) computer.
Mentions: The customized visible and near-infrared (VIS/NIR) HSI system was applied. The system consisted of an image spectrograph (Imspector V10E-QE, Spectral Imaging Ltd., Oulu, Finland), a digital charge-coupled device (CCD)camera (C8484-05G, Hamamatsu Photonics, Hamamatsu, Japan), a camera lens (V23-f/2.4 030603, Specim Ltd, Oulu, Finland), illumination and a controller, a sample stage and electric moving stage, a dark room, and a computer (Figure 1). The line scanning image spectrograph had a spectral range of 400–1000 nm and maximum image size of 6.15 × 14.2 mm (spectral × spatial). In this study, the compression mode was set as 2 × 2 binning. The CCD camera has a high-resolution of 1344 (H) × 1024 (V), a wide dynamic range of 12-bit digital output, and high sensitivity in the VIS/NIR region. The illumination consisted of a linear light (P/N 9130, Illumination Technologies, Inc., Elbridge, NY, USA) and a light-scattering cylinder to make the light uniform and even. In order to prevent images from being blurred or deformed, the intensity of illumination, the speed of the electric moving stage, the exposure time of the camera, and the object distance were all set at appropriate values. The object distance was set at 420 mm, the speed of the electric moving stage was fixed at 2.8 mm/s, and the exposure time was set at 90 ms.

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