A New Perspective for Flexible Feature Gathering in Scene Text Recognition Via Character Anchor Pooling
This addresses the problem of recognizing irregularly shaped text in natural scenes for computer vision applications, representing a novel method rather than an incremental improvement.
The paper tackles irregular scene text recognition by proposing Character Anchoring Module (CAM) and Anchor Pooling Module (APM) to extract features in a shape-insensitive way, achieving state-of-the-art performance on irregular datasets like ICDAR 2015, CUTE, and Total-Text while matching SOTA on regular datasets.
Irregular scene text recognition has attracted much attention from the research community, mainly due to the complexity of shapes of text in natural scene. However, recent methods either rely on shape-sensitive modules such as bounding box regression, or discard sequence learning. To tackle these issues, we propose a pair of coupling modules, termed as Character Anchoring Module (CAM) and Anchor Pooling Module (APM), to extract high-level semantics from two-dimensional space to form feature sequences. The proposed CAM localizes the text in a shape-insensitive way by design by anchoring characters individually. APM then interpolates and gathers features flexibly along the character anchors which enables sequence learning. The complementary modules realize a harmonic unification of spatial information and sequence learning. With the proposed modules, our recognition system surpasses previous state-of-the-art scores on irregular and perspective text datasets, including, ICDAR 2015, CUTE, and Total-Text, while paralleling state-of-the-art performance on regular text datasets.