Knowledge Commons of Institute of Automation,CAS
Adaptive Scaling and Reffned Pyramid Feature Fusion Network for Scene Text Segmentation | |
Li TZ(李天佐)![]() ![]() ![]() ![]() | |
发表期刊 | ICDAR2024
![]() |
2024 | |
页码 | 1 |
文章类型 | 国际会议 |
摘要 | Although scene text recognition has achieved high performance, text segmentation still needs to be improved. The goal of text segmentation is to obtain pixel-level foreground text masks from scene images. In this paper, we adaptively resize the input images to their optimal scales and propose the Reffned Pyramid Feature Fusion Network (RPFF-Net) for robust scene text segmentation. To address the issue of inconsistent text scaling, we propose an adaptive image scaling method that takes into account the density of text regions in each scene image. In the RPFF-Net, we ffrst extract multi-scale features from the backbone network, and then combine these features using effective pyramid feature fusion methods. To enhance the interaction between texts from contextual characters and extract features at different levels, we apply two self-attention mechanisms to the fusion feature map in spatial and channel dimensions. The experimental results demonstrate the effectiveness of our approach on several text segmentation benchmarks including the monolingual TextSeg and bilingual BTS dataset, and show that it outperforms the existing state-of-the-art scene text segmentation methods even without OCR (optical character recognition) enhancement. |
语种 | 英语 |
七大方向——子方向分类 | 文字识别与文档分析 |
国重实验室规划方向分类 | 视觉信息处理 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/57528 |
专题 | 多模态人工智能系统全国重点实验室_模式分析与学习 |
推荐引用方式 GB/T 7714 | Li TZ,Zhang H,Li XH,et al. Adaptive Scaling and Reffned Pyramid Feature Fusion Network for Scene Text Segmentation[J]. ICDAR2024,2024:1. |
APA | Li TZ,Zhang H,Li XH,&Yin F.(2024).Adaptive Scaling and Reffned Pyramid Feature Fusion Network for Scene Text Segmentation.ICDAR2024,1. |
MLA | Li TZ,et al."Adaptive Scaling and Reffned Pyramid Feature Fusion Network for Scene Text Segmentation".ICDAR2024 (2024):1. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Adaptive Scaling and(982KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论