Symbols Detection and Classification using Graph Neural Networks

Abstract

• The paper proposes a method based on Graph Neural Networks to extract and classify symbols on floorplans • The experimental comparison of several models shows the relevance of integrating structural information • The paper provides a first empirical evidence that machine learning can be used to solve a subgraph isomorphism problem In this paper, we propose a method to both extract and classify symbols in floorplan images. This method relies on the very recent developments of Graph Neural Networks (GNN). In the proposed approach, floorplan images are first converted into Region Adjacency Graphs (RAGs). In order to achieve both classification and extraction, two different GNNs are used. The first one aims at classifying each node of the graph while the second targets the extraction of clusters corresponding to symbols. In both cases, the model is able to take into account edge features. Each model is firstly evaluated independently before combining both tasks simultaneously, increasing the quickness of the results.