AI 版面分析
文档版面分析：输出文档图片中图、表、标题、文本的位置和文本信息
- Document layout analysis: Output the position and text information of the graph, table, title, text in the document picture
在传统的文档OCR识别技术中，算法会先分析图片中有几个布局区域，然后分析出水平横向文字，竖向垂直文字，表格和配图照片等区域，然后在针对各自的特点进行切分字符，保留区域类型，进行OCR识别调整；所以可以适应各种类型的文本识别。有些小角度的倾斜文本，OCR程序也可以进行智能调整识别；
- In the traditional document OCR recognition technology, the algorithm firstly analyzes several layout areas in the picture, and then analyzes horizontal and horizontal text, vertical and vertical text, table and picture matching areas, etc., and then performs character segmentation according to their respective characteristics, preserves the area type, and carries out OCR recognition adjustment.So it can adapt to all kinds of text recognition.OCR program can also intelligently adjust and recognize some small Angle slanted text.
AlexNet网络 +
测得到高
精度的
结果图