电脑技术

电脑技术

+关注 已有 2 人关注
暂无版块简介,请联系管理员或版主
版主: james007, legs+
今日: 0|主题: 1293|排名: 43  收藏本版 (2) |订阅
https://hyrule.readthedocs.io/en/master/index.html
https://hymn.readthedocs.io/en/latest/intro.html
https://github.com/DelpherNL/Open-Newspaper-Archive
https://docs.hylang.org/en/stable/tutorial.html (setv fruit ["apple" "banana" "cantaloupe"]) (print (get fruit 0)) ; => apple (setv (get fruit 1) "durian") (pr ...
ImageFont.truetype(font="simsun.ttc", size=18, encoding="utf-8")
hOCR更像Word文档,布局严谨,Alto XML可以容纳各种复杂图形
from PIL import Image import pytesseract pytesseract.pytesseract.tesseract_cmd = r'C:/Users/Dell/AppData/Local/Tesseract-OCR/tesseract.exe' # Get ALTO ...
https://github.com/altoxml/schema/blob/master/v4/alto-4-0.xsd
https://pypi.org/project/alto-xml/ from alto import parse_file alto = parse_file('path/to/alto/file.xml') print(alto.extract_words())
https://www.cnblogs.com/moon1992/p/5092726.html
https://blog.csdn.net/lukas_ten/article/details/115149086
https://mp.weixin.qq.com/s?src=11×tamp=1649865674&ver=3736&signature=MGC8mTXXxXugS36Lnb8UJTJdIe3V1cd5swryZFLZKjcf0nTTvFoWOP8p9zkJrcCywF4opmQ*U*mKtcodR7NPLt ...
# import using ``mh`` abbreviation which is common: import mahotas as mh # Load one of the demo images im = mh.demos.load('nuclear') # Automatically compute a ...
链接:https://blog.csdn.net/weixin_42627541/article/details/117764031
比如版面重建,做成可编辑版面,还要对它的语言进行分析,以便后期自动翻译
识别并重建复杂的版式和图形 实现世界上所有文字,手写体的识别
https://blog.advance.ai/blog/technologies-in-machine-learning-based-ocr-and-its-further-directions
https://readcoop.eu/transkribus/public-models/
用Scihub下载这篇论文,英文的,看得懂的病友可以参考 https://dl.acm.org/doi/10.1145/3355610
https://www.imagetotext.io/docs/#get-apigetuserinfo
下一页 »
快速发帖
还可输入 80 个字符
您需要登录后才可以发帖 登录 | 立即注册

本版积分规则

发表新帖

Archiver|手机版|小黑屋|免责及版权声明|关于|美丽心灵公益论坛