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

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.

Maize Seed Variety Classification Using the Integration of Spectral and Image Features Combined with Feature Transformation Based on Hyperspectral Imaging

“…The 11 optimal wavelengths selected by SPA for one random run are shown in Figure 5. The most selected wavelengths for maize seed classification were located in the region of 500-750 nm, and they mainly reflected the absorption of starch and oil contained in seed [16]. To consider comprehensively the speed of data acquisition and processing as well as classification accuracy, the number of optimal wavelengths was set to 11 in this study.…”

“…The 11 optimal wavelengths selected by SPA for one random run are shown in Figure 5. The most selected wavelengths for maize seed classification were located in the region of 500-750 nm, and they mainly reflected the absorption of starch and oil contained in seed [16]. …”

“…Wang et al [15] used spectral and textural features (i.e., short-run emphasis, long-run emphasis, gray-level non-uniformity, run-length non-uniformity, and run percentage) extracted from six optimal wavelengths to develop the LS-SVM model for classifying the three variety of waxy maize and achieved classification accuracy of 88.89%. Yang et al [16] reported a 98.2% prediction accuracy in classifying four varieties of maize seed using the combination of spectra, morphologic features (i.e., area, circularity, aspect ratio, roundness, and solidity) and texture features (i.e., energy, contrast, correlation, entropy, and standard deviations) extracted from the 19 optimal wavelengths for germ side. However, only part of the image features was used to classify a small number of varieties in their experiments.…”

Multispectral band selection for imaging sensor design for vineyard disease detection: case of Flavescence Dorée

“…Finally, each model is evaluated and the optimal candidate subset is chosen according to its performance. This technique was used in many studies such as (Zhang et al, 2013) or (Yang et al, 2015). The classification task was applied using 2 classifiers: the Discriminant Analysis (DA) and the Support Vector Machine (SVM), as these are the most widely used in the literature.…”

Spectral Similarity Assessment Based on a Spectrum Reflectance-Absorption Index and Simplified Curve Patterns for Hyperspectral Remote Sensing

“…In recent years, hyperspectral remote sensing technologies have developed rapidly and are being widely applied in many industries. Remote sensing image classification has evolved from rough recognition using multi-spectral images to undertake spectrum-analysis-based fine identification using hyperspectral images [2,3]. However, due to the increased cost of hyperspectral remote sensing image data volume, high correlation among the bands and training samples, the traditional hyperspectral remote sensing image classification and recognition technologies cannot satisfy the requirements of hyperspectral remote sensing applications [4].…”