关于Tesseract-OCR生成box文件时报错empty page

最新推荐文章于 2021-02-20 15:12:00 发布

fireabcdefg

最新推荐文章于 2021-02-20 15:12:00 发布

阅读量6k

点赞数 9

文章标签： tesseract 图片识别

本文链接：https://blog.csdn.net/fire669842703/article/details/103009578

版权

windows10

jdk1.8.0_144

1.以管理员身份打开命令行

2.生成box文件常规命令行如下：

tesseract.exe num.font.exp0.tif num.font.exp0 batch.nochop makebox

但是命令行中会出现很多empty page，查阅文档，发现tesseract 是可以设置psm参数的，如下参数引用于https://blog.csdn.net/weixin_30323631/article/details/96397131：

Usage:tesseract imagename outputbase [-l lang] [-psm pagesegmode] [configfile...]
pagesegmode values are:
0 = Orientation and script detection (OSD) only.
1 = Automatic page segmentation with OSD.
2 = Automatic page segmentation, but no OSD, or OCR
3 = Fully automatic page segmentation, but no OSD. (Default)
4 = Assume a single column of text of variable sizes.
5 = Assume a single uniform block of vertically aligned text.
6 = Assume a single uniform block of text.
7 = Treat the image as a single text line.
8 = Treat the image as a single word.
9 = Treat the image as a single word in a circle.
10 = Treat the image as a single character.
-l lang and/or -psm pagesegmode must occur before anyconfigfile.

tesseract imagename outputbase [-l lang] [-psm pagesegmode] [configfile...]

tesseract 图片名输出文件名 -l 字库文件 -psm pagesegmode 配置文件

于是采用了tesseract.exe num.font.exp0.tif num.font.exp0 --psm 7 batch.nochop makebox生成box文件，没有报错了