The generalization capability is usually recognized as the most desired feature of data-driven learning systems, such as classifiers. However, in many practical applications obtaining human-understandable information, relevant to the problem at hand, from the classidication model can be equally important. In this paper we propose a classification system able to fulfill these two requirements simultaneously for a generic image classification task. As a first preprocessing step, an input image to the classifier is represented by a labeled graph, relying on a segmentation algorithm. The graph is conceived to represent visual and topological information of the relevant segments of the image. Then, the graph is classified by a suited inductive inference engine. In the learning procedure all the training set images are represented by graphs, feeding a state-of-the-art classification system working on structured domains. The synthesis procedure consists in extracting characterizing subgraphs
An interpretable graph-based image classifier / Bianchi, FILIPPO MARIA; Scardapane, Simone; Livi, Lorenzo; Uncini, Aurelio; Rizzi, Antonello. - STAMPA. - (2014), pp. 2339-2346. (Intervento presentato al convegno IJCNN 2014 - International Joint Conference on Neural Networks tenutosi a Beijing; China nel July 6-11) [10.1109/ijcnn.2014.6889601].
An interpretable graph-based image classifier
BIANCHI, FILIPPO MARIA;SCARDAPANE, SIMONE;LIVI, LORENZO;UNCINI, Aurelio;RIZZI, Antonello
2014
Abstract
The generalization capability is usually recognized as the most desired feature of data-driven learning systems, such as classifiers. However, in many practical applications obtaining human-understandable information, relevant to the problem at hand, from the classidication model can be equally important. In this paper we propose a classification system able to fulfill these two requirements simultaneously for a generic image classification task. As a first preprocessing step, an input image to the classifier is represented by a labeled graph, relying on a segmentation algorithm. The graph is conceived to represent visual and topological information of the relevant segments of the image. Then, the graph is classified by a suited inductive inference engine. In the learning procedure all the training set images are represented by graphs, feeding a state-of-the-art classification system working on structured domains. The synthesis procedure consists in extracting characterizing subgraphsI documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.