智能系统学报2024，Vol.19Issue(6)：1503-1517,15.DOI:10.11992/tis.202307012
改进单点定位模型的轻量级端到端文本识别方法
A lightweight end-to-end text recognition method based on SPTS
摘要
Abstract
Addressing the problems of slow reasoning speed and the large number of model parameters in existing text spotting methods,this paper presents a lightweight end-to-end text spotting method based on single-point scene text spotting.First,PP-LCNet was introduced as the backbone network for feature extraction.Then,a three-local channel at-tention module was designed before the decoder,utilizing three different scales of one-dimensional convolution to en-hance information interaction between channels.Next,a locally enhanced attention module was proposed to replace the feedforward network component in the original decoder,thereby improving the spatial correlation of text features using depthwise separable convolution.Subsequently,a token selector module was added after each decoder layer to highlight text features with saliency markers and reduce the accumulation of irrelevant pixels.Finally,recognition results were predicted using an autoregressive decoding method.The proposed method was tested on three datasets,namely,Total-Text,CTW1500,and ICDAR2015,and then compared with six advanced methods(ABCNet,MANGO,ABCNet v2,SPTS,SwinTextSpotter,and TESTR).Compared to the SPTS method,the proposed method achieved increments in in-ference speed of 19.6,35.7,and 21.1 frames/s,respectively,and reduced the number of parameters by 70.7%,demon-strating its effectiveness.关键词
注意力模块/自回归解码/轻量级网络/单点定位/文本识别/端到端/编码器/解码器Key words
attention module/autoregressive decoder/lightweight network/single point position/text spotting/end to end/encoder/decoder分类
信息技术与安全科学引用本文复制引用
曹锦纲,张泽恩,张铭泉..改进单点定位模型的轻量级端到端文本识别方法[J].智能系统学报,2024,19(6):1503-1517,15.基金项目
中央高校基本科研业务费专项项目(2021MS092). （2021MS092）
