How to annotate the image semantic automatically in order to across semantic gap between the feature and the high-level semantic of the image is a difficult problem.
如何跨越图像底层特征和高层语义之间的语义鸿沟，使机器自动的实现图像语义标注更是研究的难点。
As the text with high-level semantic feature and plays an important role on understanding, indexing and retrieval image content.
由于文字具有高级语义特征，对图片内容的理解、索引、检索具有重要作用，因此，研究图片文字提取具有重要的实际意义。
应用推荐