基于双分支序列残差注意力的场景文本图像超分辨率重建

Scene Text Image Super-Resolution Reconstruction Based on Dual-Branched Sequence Residual Attention

针对现有场景文本图像超分辨率重建方法存在的重建文本图像细节信息丢失和边缘模糊的问题,提出一种基于双分支序列残差注意力的重建方法DSRASRN。首先,DSRASRN采用一种新的双分支序列残差注意力模块(DSRAB),该模块采用双分支结构分别专注于水平和垂直方向上的上下文信息提取,并通过高效通道注意力(ECA)机制给予重要信息更高的权重,以增强特征的表达;其次,在DSRASRN内新增文本边缘感知模块(TEAB),增强对文本图像边缘细节和纹理的处理,TEAB采用特定方向的卷积核捕捉特定空间方向上的信息,同时结合具有不同空洞率的空洞卷积来扩大感受野并增强对高频信息的重建能力。在真实场景文本图像数据集TextZoom上的实验结果表明,DSRASRN不仅可以重建出更多的图像细节信息,而且在提高文本识别准确率方面也表现出明显优势。与TSRN、TBSRN、TG、TPGSR方法相比,DSRASRN的峰值信噪比(PSNR)分别提升0.27、0.78、0.59和0.51 dB,且DSRASRN可以使文本识别器ASTER、MORAN和CRNN的平均文本识别精度分别达到65.0%、62.1%和52.0%。此外,真实场景文本识别图像数据集ICDAR2015和SVT上的测试结果表明DSRASRN具有良好的泛化能力。

This paper proposes Dual-branch Sequence Residual Attention for Super-resolution Reconstruction Network(DSRASRN)to address the drawbacks of loss of detail information and edge blurring in text images reconstructed by existing scene text image super-resolution reconstruction methods.In DSRASRN,first,a Dual-branch Sequence Residual Attention Block(DSRAB)is adopted to obtain a more comprehensive and accurate representation of contextual information.DSRAB uses a dual-branch structure to extract horizontal and vertical context information and adopts an Efficient Channel Attention(ECA)mechanism to assign higher weights to more important information,thereby enhancing the expression ability of the captured features.Second,DSRASRN adds a Text Edge Awareness Block(TEAB)to enhance the processing of edge details and textures of text images.In TEAB,convolution kernels are applied to capture information in specific spatial directions,and a dilated convolution with different dilation rates to increase the ability to reconstruct high-frequency information is adopted.DSRASRN and four state-of-the-art reconstruction methods:TSRN,TBSRN,TG,and TPGSR are evaluated on the TextZoom dataset.Experimental results show that DSRASRN reconstructs text images with more detail and exhibits superior performance by achieving higher text recognition accuracy.Compared with the other four evaluated methods,DSRASRN improves Peak Signal-to-Noise Ratio(PSNR)by up to 0.27,0.78,0.59,and 0.51 dB,respectively.The average text recognition accuracies of ASTER,MORAN,and CRNN are 65.0%,62.1%,and 52.0%,respectively.In addition,the generalization ability of DSRASRN was evaluated on the ICDAR2015 and SVT datasets.The experimental results show that DSRASRN achieves good generalization.