In order to solve the problem that the fuzziness and uncertainty of real data may seriously affect the classification results of few-shot learning, a Fuzzy Prototype Network (FPN) based on fuzzy reasoning was proposed by improving and optimizing the traditional few-shot learning prototype network. Firstly, the image feature information was obtained from Convolutional Neural Network (CNN) and fuzzy neural network, respectively. Then, linear knowledge fusion was performed on the two obtained parts of information to obtain the final image features. Finally, to achieve the final classification effect, the Euclidean distance between each category prototype and the query set was measured. A series of experiments were carried out on the mainstream datasets Omniglot and miniImageNet for few-shot learning classification. On miniImageNet dataset, the model achieves accuracy of 49.38% under the experimental setting of 5-way 1-shot, accuracy of 67.84% under the experimental setting of 5-way 5-shot, and accuracy of 51.40% under the experimental setting of 30-way 1-shot; and compared with the traditional prototype network, the model also has the accuracy greatly improved on Omniglot dataset.

Coupled data fusion algorithms mainly improve estimation accuracy and explain related latent variables of the other coupled data sets by using the information of one data set. Aiming at the large number of coupled images existing in reality, based on the Coupled Matrix and Tensor Factorization-OPTimization (CMTF-OPT) algorithm in coupled data fusion, a Coupled Images Factorization-OPTimization (CIF-OPT) algorithm for coupled images was proposed. The corresponding theoretical analysis and experimental results show that the effects of coupled image fusion by CIF-OPT algorithm under different noise influence are robust, and better than those by other coupling algorithms. Particularly, the CIF-OPT algorithm can accurately restore an image of missing some data elements with its coupled image at a certain probability.