Automatic reading texts in scenes is an attracting increasing interest in recent years due to various context awareness applications. Leverage on the advantages of object proposal in generic object detection, we propose a max-pooling based scene text proposal technique aiming for automatic extraction of texts in scenes. Given a scene image, a max-pooling based grouping technique is designed to search for scene text proposals within a feature map which is computed from image edges. Searched proposals are then ranked by a scoring function that is defined based on the histogram of oriented gradient. The proposed technique has been evaluated on two publicly available scene text datasets, including the ICDAR2015 dataset and the Street View Text (SVT) dataset. Experiments show that the proposed technique obtains superior proposal performance as compared with state-of-the-arts, especially when a small number of proposals is selected. In addition, it also obtains state-of-the-art scene text spotting when integrated with a scene text recognition model.
展开▼
机译：由于各种背景感知应用，近年来，场景中的自动阅读文本是一种吸引越来越多的兴趣。利用对象提案在通用对象检测中的优势，我们提出了一种基于最大池的场景文本提案技术，旨在自动提取场景中的文本。给定场景图像，基于最大池的分组技术被设计为在从图像边缘计算的特征映射内搜索场景文本提案。然后搜索的提案由评分函数进行排序，该函数是基于定向梯度的直方图定义的。所提出的技术已经在两个公开的场景文本数据集上进行了评估，包括ICDAR2015数据集和街景文本（SVT）数据集。 Experiments show that the proposed technique obtains superior proposal performance as compared with state-of-the-arts, especially when a small number of proposals is selected.此外，当与场景文本识别模型集成时，它还获得最先进的场景文本斑点。
展开▼
