FastGCN + ARSRGemb: a novel framework for object recognition

In recent years research has been producing an important effort to encode the digital image content. Most of adopted paradigms only focus on local features and lack in information about location relationships between them. To fill this gap, we propose a framework built three cornerstones. First, ARSRG (Attributed Relational SIFT (Scale-Invariant Feature Transform) regions graph), for representation, is adopted. Second, graph embedding model, with purpose work simplified vector space, applied. Finally, Fast Graph Convolutional Networks perform classification phase based dataset representation. The evaluated state art object recognition datasets through wide experimental compared well-known competitors.