Aurora Image Classification Based on Global Features 基于全局特征.PDF

Computer Science and Application 计算机科学与应用, 2017, 7(4), 369-376 Published Online April 2017 in Hans. /journal/csa /10.12677/csa.2017.74045 Aurora Image Classification Based on Global Features Zhenting Cao, Xuan Wang School of Physics and Information Technology, Shanxi Normal University, Xi’an Shaanxi th rd th Received: Apr. 10 , 2017; accepted: Apr. 23 , 2017; published: Apr. 30 , 2017 Abstract Aurora classification is of great significance to the research on the way and degree of the influence of solar activity on the earth. The existing methods for aurora image classification are mainly based on the local features extracted from the aurora images. These local features are sensitive to noise and variances of the position and orientation, so their classification accuracies and robust- ness are insufficient for complicated applications. This paper proposed a novel aurora image clas- sification method based on the global feature descriptors. In the proposed method, the aurora image is projected to Radon domain via Radon transform, and then, the variances of columns are determined, the rotation invariant features are obtained via circular shift operation on the va- riance sequence to let the maximum value in the first place, which completes the rotation norma- lization of the variance sequence. A nearest neighbor classifier based on Euclidean distance is used for classification. Experimental results show that the proposed approach yields a better per- formance in terms of the correct classification percentages compared with the aurora image clas- sification method based on representative local feature. It is also shown that the proposed