利用机器视觉识别麦粒内米象发育规律与龄期

研究麦粒内部粮虫生长规律,判断粮虫所处发育龄期,为制定合理的防治措施提供科学依据,具有重要的社会经济价值。该文提出一种基于机器视觉的麦粒内米象变态发育规律及龄期识别研究方法。试验利用Micro-CT获取侵染麦粒投影数据,应用z-FDK(z-Feldkamp-Davis-Kress)算法重建出侵染粒的二维图像,利用图像分割及形态学方法得到虫体图像。提取了虫体的8个二维特征、4个三维特征、7个不变矩特征和7个基于灰度共生矩阵的显著性纹理特征,构成26维原始特征空间。根据不同龄期虫体特征的变化,研究米象在麦粒内的变态发育规律。利用模拟退火算法(simulated annealing algorithm,SAA)优化虫体原始特征,构建了优化后的10维特征空间。运用人工蜂群算法(artificial bee colony,ABC)优化支持向量机(support vector machine,SVM)的惩罚因子和径向基核函数参数,实现对麦粒内米象所处发育龄期的自动判别。试验结果表明,米象变态发育规律与实际情况一致,且对米象龄期的识别率达到97%,可有效判别出侵染粒中米象所处发育龄期。

Identifying larval development of Sitophilus oryzae in wheat grain using computer vision

Abstract: Sitophilus oryzae is a weevil growing on diet of wheat grain. Its timely identification and control is essential to safeguarding wheat production. This paper proposes a computer vision-based method to diagnose its larval development inside wheat grain. After Sitophilus oryzae infects grains, its subsequent development is divided into egg stage, juvenile stage, elder stage, pupal stage and adult stage. We acquired a sequence of micro-CT projection images of the infested grains and then reconstructed the 2D images using the FDK algorithm. The larvae in the images were mapped out using segmentation and morphological method. Overall, we extracted 26 features to characterize a larva and its development, including morphological features, 3D features, invariant moment and texture features. The metamorphosis of Sitophilus oryzae was differentiated based on larval height, larval volume, its cross-sectional area, the minimum rectangle method, surficial area and perimeter of the cross section. The partial features simulated using the annealing algorithm composed of optimal features which were calculated by the fitness function, with the initial temperature T set at 150, drop rate at 0.9 and the end temperature at 1.0. Ten features were determined after 10 optimizations and the associated maximum fitness was 90.214 3%. The penalty factor c and the kernel function parameter g in the support vector machine (SVM) were optimized by the artificial bee colony (ABC) algorithm, in which the initial bee colony size was 20, the times of updates was set to be 50 and the maximum number of iterations was 50. Two parameters were optimized in the range of 0.01-100, and the algorithm was repeated twice to check robustness of the program. We used 250 images to train and test the model. The model correctly identified 97% of the larvae at different developmental stages when the parameters the penalty factor c=96.44, and the kernel function parameter g=0.01. The results showed that the height of Sitophilus oryzae larva had been in increase in the experiment; its volume, cross-sectional area, size of the minimum rectangle, surficial area and perimeter of cross-section had all asymptotically increased up to the pupal stage, followed by a decline after that. In addition, ABC-SVM correctly identified 97 images. The results presented in this paper indicated that computer vision can be used to identify larval development of Sitophilus oryzae in wheat grain.