Foto del docente

Andrea Asperti


Department of Computer Science and Engineering

Academic discipline: INF/01 Informatics


Avviso di seminario

Il giorno martedi 30 aprile alle ore 12 il Dr. Manuel García-Domínguez dell'Universita di La Rioja (Spain) terra' il seguente seminario:

luogo: Sala Seminario Busi, DISI, Mura Anteo Zamboni 7

titolo: FrImCla: A Framework for Image Classification using Traditional and Transfer Learning Techniques

Abstract: Deep learning techniques are currently the state of the art approach to deal with image classification problems in bioimaging. Nevertheless, life scientists might find challenging the use of these techniques due to several reasons, including the lack of enough images, the necessity of trying different models and conducting a thorough comparison of the results obtained with them, and the technical difficulties of employing different libraries, tools and special purpose hardware like GPUs. In this talk, we present the FrImCla framework, an open-source and free tool that simplifies the construction of robust models for image classification from a, even small, dataset of images, and only using the computer CPU. Given a dataset of annotated images, FrImCla automatically constructs a classification model by trying several feature extractors (based both on transfer learning and traditional computer vision methods) and machine learning algorithms, and selecting the best combination after a thorough statistical analysis. Thanks to FrImCla, users in life sciences, but also in other contexts, can use state-of-the-art techniques and build accurate classification models from small datasets, and without requiring any special hardware.


Published on: April 24 2019