Deep Matching Prior Network: Toward Tighter Multi-oriented Text Detection
来源:互联网 发布:java 读取文件字符串 编辑:程序博客网 时间:2024/06/04 00:46
Retrospective research has only focused on using rectangular bounding box or horizontal sliding window to localize text, which may result in redundant background noise, unnecessary overlap or even information loss. To address these issues, we propose a new Convolutional Neural Networks (CNNs) based method, named Deep Matching Prior Network (DMPNet), to detect text with tighter quadrangle.
quadrangle 四边形
- firstly, roughly recalling text with quadrilateral sliding window
- then, using a shared Monte-Carlo method for fast and accurate computing of polygonal areas;
- finely localizing text with quadrangle and design a Smooth Ln loss for
moderately adjusting the predicted bounding box.
设计多几个sliding window
改进计算overlap的方式
回归十个参数
In future, we will explore using shape-adaptive sliding windows toward tighter scene text detection.
阅读全文
0 0
- Deep Matching Prior Network: Toward Tighter Multi-oriented Text Detection
- Deep Matching Prior Network: Toward Tighter Multi-oriented Text Detection 论文笔记
- 论文阅读-《Deep Matching Prior Network:Towards Tighter Multi-oriented Text Detection》
- 【论文阅读】Fused Text Segmentation Network for Multi-oriented Scene Text Detection
- [水水文]Fused Text Segmentation Networks for Multi-oriented Scene Text Detection
- DeepID-Net:multi-stage and deformable deep convolutional neural network for object detection
- 论文笔记 MSCNN:A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection
- MSCNN 论文解析(A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection
- MSCNN 论文解析(A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection
- [论文解读] MSCNN: A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection
- 目标检测--A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection
- Switchable Deep Network for Pedestrian Detection(泛读)
- Deep Network Flow for Multi-Object Tracking
- Query-Oriented Multi-Document Summarization via Unsupervised Deep Learning
- 【论文笔记】 Arbitrary-Oriented Scene Text Detection via Rotation Proposals
- 论文笔记-Arbitrary-Oriented Scene Text Detection via Rotation Proposals
- [论文笔记]Arbitrary-Oriented Scene Text Detection via Rotation Proposals
- Saliency Detection by Multi-Context Deep Learning 读后笔记
- explain分析
- http header详解
- 【枚举Day1】20170529-2枚举算法专题练习 题解
- CSS3新特性汇总
- sql多表查询
- Deep Matching Prior Network: Toward Tighter Multi-oriented Text Detection
- 积分系统(6)-CSS+JS+bootstrap 等在系统中的封装红利
- Java动态配置Quartz调度任务集成到spring(一)
- nginx配置点播服务
- 不重新编译为PHP增加LDAP模块的支持
- 记录一个很好用的大文本编辑查看器记录一下 PilotEdit
- HDUoj 1078
- Linux Command Line and....ch3(基本的bash shell)
- 【数论Day1】 最大公约数(gcd)题目