计算机工程与应用2024，Vol.60Issue(1)：198-206,9.DOI:10.3778/j.issn.1002-8331.2207-0410
基于多尺度注意力特征融合的场景文本检测
Text Detection Algorithm Based on Multi-Scale Attention Feature Fusion
摘要
Abstract
Aiming at the low detection accuracy of small scale text and long text in text detection,a scene text detection algorithm based on multi-scale attention feature fusion is proposed.This method takes Mask R-CNN as the baseline model,selects Swin_Transformer as the backbone network to extract the bottom features.In the feature pyramid networks(FPN),the multi-scale attention heat maps are fused with the bottom features through lateral connection,so that different layers of the detector focus on specific scale targets,and the vertical feature sharing in FPN structure is realized by using the relationship between the adjacent attentional heat maps,avoiding the inconsistency of gradient calculation among different layers.Experimental results demonstrate that the accuracy,recall and F-value of this method reach 88.3%,83.07%and 85.61%respectively on ICDAR2015 data set,and it performs well than the existing methods on CTW1500 and Total-Text curved text data set.关键词
场景文本检测/Mask R-CNN/Swin Transformer/注意力机制/多尺度特征融合Key words
scene text detection/Mask R-CNN/Swin Transformer/attention mechanism/multi-scale feature fusion分类
信息技术与安全科学引用本文复制引用
厍向阳,刘哲,董立红..基于多尺度注意力特征融合的场景文本检测[J].计算机工程与应用,2024,60(1):198-206,9.基金项目
陕西省自然科学基础研究(2019JLM-11) （2019JLM-11）
陕西省科技计划(2021JQ-576) （2021JQ-576）
陕西省教育厅项目(19JK0526). （19JK0526）
