Cloud picture classification method based on multi-modal data

The embodiment of the invention discloses a cloud picture classification method based on multi-modal data, and the method comprises the steps: obtaining the multi-modal data which comprises image data and numerical data; preprocessing the image data so as to remove noise in the image data and perform data enhancement; performing feature extraction on the preprocessed image data by using an attention-guided capsule network; fusing the features extracted by the capsule network with the numerical data; and processing the fused data to obtain a classification result. According to the method, the classification accuracy can be improved. 本申请实施例公开了一种基于多模态数据的云图分类方法，包括：获取多模态数据，所述多模态数据包括图像数据和数值数据；对所述图像数据进行预处理，以去除所述图像数据中的噪声并进行数据增强；用注意力引导的胶囊网络对预处理后的所、述图像数据进行特征提取；将所述胶囊网络提取的特征与所述数值数据进行融合；对融合后的数据进行处理，得到分类结果。本申请实施例的方法能够提高分类的准确性。