Geometric Deep Learning for Enhancing Irregular Scene Text Detection

Text detection in natural scene images presents significant challenges, particularly in detecting irregular shapes. As a result of the limited receptive field of CNNs, existing methods have difficulty capturing long-range relationships between distant component regions. This study introduces an innovative method for identifying irregular text in images of natural scenes. The approach utilizes a U-net architecture combined with connected component analysis, resulting in improved accuracy in detecting text components and reducing the identification of non-character text components. Additionally, our strategy incorporates the use of graph convolution networks (GCN) to deduce adjacency relations among text components. The integration of GCNs introduces a sophisticated mechanism for inferring adjacency relations, contributing significantly to the advancement of text detection in natural scene images. Our method's efficacy is showcased through experimental assessments on three publicly available datasets: "ICDAR2013," "CTW-1500," and "MSRA-TD500."