-
I would like to call kraken recognition from code and get hocr. However, just calling `kraken --hocr -i image.png image.txt binarize segment ocr --reorder` will initialize model on each image recognit…
-
### Environment
* **Tesseract Version**: v4.00.00dev-692-gad5ee18 with Leptonica
* **Commit Number**: ad5ee18
* **Platform**: MAC OS 16.7.0 Darwin Kernel Version 16.7.0: Thu Jun 15 17:36:27 PDT 2…
-
Key | Value
-- | --
Title |The University of Kansas science bulletin
BHL Title ID | [3179](https://www.biodiversitylibrary.org/bibliography/3179)
ISSN | 0022-8850
Thumbnail |
Segmentation | Ma…
swlny updated
4 months ago
-
I just found that the new PAGE-XML editing facility still has one bug: it does not retain `AlternativeImage` under their original segment (which could be region, line, word or even glyph), but moves t…
-
Hey buddy, this new update is incredible. I was absolutely blown away. Being able to edit the translated text already solves most of my problems.
I just have one small favor to ask. As you can see …
-
Please refer to the following link:
https://github.com/tesseract-ocr/tesseract/pull/2635
This concerns changes made to lstm_choices_mode.
Unless I misunderstand what these options are suppose…
-
I get an "urlList is empty, failed to detect cloud text" error when I try to recognize the text from the Album right in your sample code.
Please fix it
-
### 请提出你的问题
当输入图片,输出预测结果时,会出现某个字段的预测box是正确的,但是box中包含的字符存在缺失的情况
在确定预测的box包含的字符这一步,会用到计算字符宽度的逻辑,这个字符宽度目前是用的平均宽度,实际上 一行文本同时包含 中文、数字、字母时,每个字符宽度是不一样的,那么此处使用平均宽度来计算当前字符box是否在预测的box中, 会判断错误
代码中计算字符宽…
-
root@ubuntu:/home/administrator/tesseract-master# /usr/local/bin/text2image --text=/home/administrator/langdata/chi_sim/chi_sim.training_text --fontconfig_tmpdir=/tmp/font_tmp.HKWX4LOUh0 --fonts_dir=…
-
Currently you have to depend on README to know the APIs, by adding types you can help save time in development. It should be easy since everything is already documented though. Should I make a PR?
sglkc updated
2 weeks ago