Application of Joint Skewness Algorithm to Select Optimal Wavelengths of Hyperspectral Image for Maize Seed Classification YANG Sai, ZHU Qi-bing*, HUANG Min

As an effective method for the nondestructive measurement of agricultural products quality, hyperspectral imaging technology has been widely studied in the field of seed classification and identification. Feature extraction and optimal wavelength selection are the two critical issues affecting the application of hyperspectral image in the field of seed identification. This study aimed to select optimal wavelengths from hyperspectral image data using joint skewness algorithm, so that they can be deployed in multispectral imaging-based inspection system for the automatic classification of maize seed. The hyperspectral images covering the wavelength range of 438～1 000 nm were acquired for 960 maize seeds including 10 varieties. After extracting the mean spectrum and entropy from the hyperspectral images, the joint skewness algorithm was used to select optimal wavelengths, and the classification models based on support vector machine were developed using the mean spectrum, entropy, and their combination, respectively. The experimental results indicated that the classification accuracy of the models developed by combination of the mean spectrum and entropy were higher than that of the mean spectrum or entropy for either full wavelengths or optimal wavelengths. The classification model for the combination of the mean spectrum and entropy based on the 10 optimal wavelengths selected by the joint skewness algorithm obtained 96.28% accuracy for test samples, with improvements of 4.30% and 20.38% over that of the mean spectrum and entropy, respectively, which was higher than the classification accuracy of the model that developed in the full wavelength (i.e., 93.47%). Meanwhile, the classification model based on joint skewness algorithm yielded the better classification accuracy than that of uninformative viable elimination algorithm, successive projections algorithm, and competitive adaptive reweighed sampling algorithm. This study made the online application of the hyperspectral image technology available for seed identification.

[Purity Detection Model Update of Maize Seeds Based on Active Learning].

Seed purity reflects the degree of seed varieties in typical consistent characteristics, so it is great important to improve the reliability and accuracy of seed purity detection to guarantee the quality of seeds. Hyperspectral imaging can reflect the internal and external characteristics of seeds at the same time, which has been widely used in nondestructive detection of agricultural products. The essence of nondestructive detection of agricultural products using hyperspectral imaging technique is to establish the mathematical model between the spectral information and the quality of agricultural products. Since the spectral information is easily affected by the sample growth environment, the stability and generalization of model would weaken when the test samples harvested from different origin and year. Active learning algorithm was investigated to add representative samples to expand the sample space for the original model, so as to implement the rapid update of the model's ability. Random selection (RS) and Kennard-Stone algorithm (KS) were performed to compare the model update effect with active learning algorithm. The experimental results indicated that in the division of different proportion of sample set (1:1, 3:1, 4:1), the updated purity detection model for maize seeds from 2010 year which was added 40 samples selected by active learning algorithm from 2011 year increased the prediction accuracy for 2011 new samples from 47%, 33.75%, 49% to 98.89%, 98.33%, 98.33%. For the updated purity detection model of 2011 year, its prediction accuracy for 2010 new samples increased by 50.83%, 54.58%, 53.75% to 94.57%, 94.02%, 94.57% after adding 56 new samples from 2010 year. Meanwhile the effect of model updated by active learning algorithm was better than that of RS and KS. Therefore, the update for purity detection model of maize seeds is feasible by active learning algorithm.

[Maize seed identification using hyperspectral imaging and SVDD algorithm].

The sufficiency of feature extraction and the rationality of classifier design are two key issues affecting the accuracy of maize seed recognition. In the present study, the hyperspectral images of maize seeds were acquired using hyperspectral image system, and the image entropy of maize seeds for each wavelength was extracted as classification features. Then, support vector data description (SVDD) algorithm was used to develop the classifier model for each variety of maize seeds. The SVDD models yielded 94.14% average test accuracy for known variety samples and 92.28% average test accuracy for new variety samples, respectively. The simulation results showed that the proposed method implemented accurate identification of maize seeds and solved the problem of misclassification by the traditional classification algorithm for new variety maize seeds.

[Feature extraction of hyperspectral scattering image for apple mealiness based on singular value decomposition].

Apple mealiness is an important sensory parameter for classification of apple quality. Hyperspectral scattering technique was investigated for noninvasive detection of apple mealiness. A singular value decomposition (SVD) method was proposed to extract the feature/ or singular values of the hyperspectral scattering images between 600 and 1000 nm for 20 mm distance including 81 wavelengths. As characteristic parameters of apple mealiness, singular values were applied to develop the classification model coupled with partial least squares discriminant analysis (PLSDA) using the samples from different origin and different storage conditions. The classification accuracies for the two-class ("mealy" and "non-mealy") model were between 76.1% and 80.6% better than mean method (75.3%-76.5%). The results indicated that SVD method was potentially useful for the feature extraction of hyperspectral scattering images and the model developed with these features can detect the mealy and non-mealy apple, but the classification accuracies need to be improved.

[LLE-SVM classification of apple mealiness based on hyperspectral scattering image].

Apple mealiness degree is an important factor for its internal quality. hyperspectral scattering, as a promising technique, was investigated for noninvasive measurement of apple mealiness. In the present paper, a locally linear embedding (LLE) coupled with support vector machine (SVM) was proposed to achieve classification because of large number of image data. LLE is a nonlinear lowering dimension method, which reveals the structure of the global nonlinearity by the local linear joint. This method can effectively calculate high-dimensional input data embedded in a low-dimensional space manifold. The dimension reduction of hyperspectral data was classified by SVM. Comparing the LLE-SVM classification method with the traditional SVM classification, the results indicated that the training accuracy obtained with the LLE-SVM was higher than that just with SVM; and the testing accuracy of the classifier changed a little before and after dimensionality reduction, and the range of fluctuation was less than 5%. It is expected that LLE-SVM method would provide an effective classification method for apple mealiness nondestructive detection using hyperspectral scattering image technique.