As part of the activity of the NFFA-EUROPE project, we applied transfer learning techniques for image recognition, automatic categorization, and labeling of nanoscience images obtained by scanning electron microscope (SEM). Roughly 20,000 SEM images were manually classified into 10 categories to form a labeled training set which can be used as a reference set for training future neural networks in the nanoscience domain. The training set was used to retrain a convolutional neural network (Inception-v3) to perform the classification. We performed additional analysis of the classifier on a second test set to further investigate the results both on particular cases and from a statistical point of view. Our algorithm was able to successfully classify around 90% of a test dataset consisting of SEM images. Finally, we developed and deployed a semi-automatic classification tool at the SEM facility at CNR-IOM. Such tool allows any NFFA researcher using SEM instrument to upload the produced images on the local data repository, and to register their automatically generated metadata on the Information and Data Repository Platform (IDRP) developed within the JRA3 of the NFFA-EUROPE project.