In recent years, text recognition has achieved remarkable success in recognizing scanned document text. However, word recognition in natural images is still an open problem, which generally requires time consuming post-processing steps. We present a novel architecture for individual word detection in scene images based on semantic segmentation. Our contributions are twofold: the concept of WordFence, which detects border areas surrounding each individual word and a novel pixelwise weighted softmax loss function which penalizes background and emphasizes small text regions. WordFence ensures that each word is detected individually, and the new loss function provides a strong training signal to both text and word border localization. The proposed technique avoids intensive post-processing, producing an end-to-end word detection system. We achieve superior localization recall on common benchmark datasets - 92% recall on ICDAR11 and ICDAR13 and 63% recall on SVT. Furthermore, our end-to-end word recognition system achieves state-of-the-art 86% F-Score on ICDAR13.

该论文提出了一种新的基于语义分割的场景图像中单词检测的架构，使用了WordFence的概念和像素加权的softmax损失函数来保证每个单词被独立检测，从而避免了后期处理，实现了一个端到端的单词检测系统。在常见的基准数据集上，该方法取得了较高的检测召回率，并且在ICDAR13数据集上实现了最先进的86% F-score。

WordFence: 自然图像中带边框感知的文本检测