Pattern Matters: Hierarchical Correlated Strip Convolutional Network for Scene Text Recognition
Chang Liu, Junjie Lai · 2022 IEEE International Conference on Multimedia and Expo (ICME) · 2022
Many state-of-the-art scene text recognition methods leverage a pre-designed backbone for general object recognition, where general objects are usually lacking of distinctive characteristics. However, unlike general objects, texts in images are usually composed of narrow strokes and their characters often share similar attributes, e.g. texture and intensity. Such useful patterns can be deteriorated if directly employing standard convolutional networks to the scene text recognition. To solve the problem, we introduce a novel operation Strip Convolution, a specially designed convolution for extracting features of narrow strokes. And we further apply a Hierarchical Correlation strategy, adopting multi-level attention mechanisms to capture common text attributes. Based on this, we design a novel framework, named as Hierarchical Correlated Strip Convolutonal network for scene text recognition. Extensive experiments demonstrate the superiority of the proposed HCSC network, improving the accuracy of text recognition effectively.