基于多模态迭代及修正的文本识别算法
Text recognition algorithm based on multimodal iteration and cor-rection
强观臣 1张丽真 1杨茜 1熊炜 2李利荣3
作者信息
- 1. 湖北工业大学电气与电子工程学院,湖北武汉 430068
- 2. 湖北工业大学电气与电子工程学院,湖北武汉 430068;湖北工业大学太阳能高效利用及储能运行控制湖北省重点实验室,湖北武汉 430068;湖北工业大学新能源及电网装备安全监测湖北省工程研究中心,湖北武汉 430068;美国南卡罗来纳大学计算机科学与工程系,南卡罗来纳州29201
- 3. 湖北工业大学电气与电子工程学院,湖北武汉 430068;湖北工业大学太阳能高效利用及储能运行控制湖北省重点实验室,湖北武汉 430068
- 折叠
摘要
针对场景文本识别在长距离建模时容易产生信息丢失和对低分辨率文本图像表征能力较弱的问题,提出了一种基于多模态迭代及修正的文本识别算法.本文算法的视觉模型(vision model)是由 CoTNet(contextual transformer networks for visual recognition)、动态卷积注意力模块(dynamic convolution attention module,DCAM)、EA-Encoder(external attention encoder)和位置注意力机制组合而成的.其中CoTNet可以有效起到缓解长距离建模产生的信息丢失问题;DCAM在增强表征能力、专注于重要特征的同时,将重要的特征传给EA-Encoder,进而提高CoTNet和EA-Encoder之间的联系;EA-Encoder可以学习整个数据集上最优区分度的特征,捕获最有语义信息的部分,进而增强表征能力.经过视觉模型后,再经过文本修正模块(text correction model)和融合模块(fusion model)得到最终的识别结果.实验数据显示,本文所提出的算法在多个公共场景文本数据集上表现良好,尤其是在不规则数据集ICDAR2015上准确率高达85.9%.
Abstract
A text recognition algorithm based on multimodal iteration and correction is proposed to ad-dress the problems that scene text recognition is prone to information loss when modeling over long distances and weak characterization for low-resolution text images.The visual model of the algorithm in this paper is a combination of contextual transformer networks for visual recognition(CoTNet),a dynamic convolutional attention module(DCAM),an external attention encoder(EA-Encoder),and a positional attention mechanism.The CoTNet can effectively alleviate the information loss problem ari-sing from long-distance modeling.The DCAM enhances representation by focusing on the essential features while passing the critical components to the EA-Encoder,improving the connection between CoTNet and EA-Encoder.EA-Encoder learns the best distinguishing features on the entire dataset,capturing the most semantic information parts and thus enhancing representation.After the visual model,the text correction and fusion modules obtain the final recognition results.According to the ex-perimental data,the algorithm proposed in this paper performs well on several public scene text data-sets,especially on the irregular dataset ICDAR2015 with an accuracy of 85.9%.
关键词
场景文本识别/动态卷积/注意力模块/外部注意力机制/编码器Key words
scene text recognition/dynamic convolution/attention module/external attention mechanism/encoder引用本文复制引用
基金项目
国家自然科学基金(62202148)
湖北省自然科学基金(2019CFB530)
湖北省科技厅重大专项(2019ZYYD020)
国家留学基金(201808420418)
出版年
2024