针对马铃薯空心病的难以检测问题, 提出了一种基于半透射高光谱成像技术结合支持向量机(support vector machine, SVM)的马铃薯空心病无损检测方法。选取224个马铃薯样本(合格149个, 空心75个)作为研究对象, 搭建了马铃薯半透射高光谱图像采集系统, 采集了马铃薯样本半透射高光谱图像(390~1 040 nm), 对感兴趣区域内的光谱进行平均和光谱特征分析。采用变量标准化(normalize)对原始光谱进行光谱预处理, 建立了全波段的SVM判别模型, 模型对测试集样本的识别准确率仅为87.5%。为了提高模型性能, 采用竞争性自适应重加权算法(competitive adaptive reweighed sampling algorithm, CARS)结合连续投影算法(successive projection algorithm, SPA)对光谱全波段520个变量进行变量选择, 最终确定了8个光谱特征变量(454, 601, 639, 664, 748, 827, 874和936 nm), 所选8个光谱变量建立的SVM模型对马铃薯测试集的识别率为94.64%。分别采用人工鱼群算法(artificial fish swarm algorithm, AFSA)、遗传算法(genetic algorithm, GA)和网格搜索法(grid search algorithm)对SVM模型的惩罚参数c和核参数g进行优化。经过建模比较分析, 确定AFSA为最优优化算法, 最优模型参数为c=10.659 1, g=0.349 7, 确定AFSA-SVM模型为马铃薯空心病的最优识别模型, 该模型总体识别率达到100%。试验结果表明: 基于半透射高光谱成像技术结合CARS-SPA与AFSA-SVM方法能够对马铃薯空心病进行准确的检测, 也为马铃薯空心病的快速无损检测提供技术支持。

The quality of potato is directly related to their edible value and industrial value. Hollow heart of potato, as a physiological disease occurred inside the tuber, is difficult to be detected. This paper put forward a non-destructive detection method by using semi-transmission hyperspectral imaging with support vector machine (SVM) to detect hollow heart of potato. Compared to reflection and transmission hyperspectral image, semi-transmission hyperspectral image can get clearer image which contains the internal quality information of agricultural products. In this study, 224 potato samples (149 normal samples and 75 hollow samples) were selected as the research object, and semi-transmission hyperspectral image acquisition system was constructed to acquire the hyperspectral images (390~1 040 nm) of the potato samples, and then the average spectrum of region of interest were extracted for spectral characteristics analysis. Normalize was used to preprocess the original spectrum, and prediction model were developed based on SVM using all wave bands, the accurate recognition rate of test set is only 87.5%. In order to simplify the model competitive adaptive reweighed sampling algorithm (CARS) and successive projection algorithm (SPA) were utilized to select important variables from the all 520 spectral variables and 8 variables were selected (454, 601, 639, 664, 748, 827, 874 and 936 nm). 94.64% of the accurate recognition rate of test set was obtained by using the 8 variables to develop SVM model. Parameter optimization algorithms, including artificial fish swarm algorithm (AFSA), genetic algorithm (GA) and grid search algorithm, were used to optimize the SVM model parameters: penalty parameter c and kernel parameter g. After comparative analysis, AFSA, a new bionic optimization algorithm based on the foraging behavior of fish swarm, was proved to get the optimal model parameter (c=10.659 1, g=0.349 7), and the recognition accuracy of 100% were obtained for the AFSA-SVM model. The results indicate that combining the semi-transmission hyperspectral imaging technology with CARS-SPA and AFSA-SVM can accurately detect hollow heart of potato, and also provide technical support for rapid non-destructive detecting of hollow heart of potato.