Geometric Deep Learning for Enhancing Irregular Scene Text Detection
Madhuri Aluri, Uma Devi Tatavarthi · Revue d intelligence artificielle · 2024
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."