|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/easyopticalcharacterrecognition/
课程评论：没有评论
课程名称：文本提取- EasyOCR 课程概述：欢迎未来的开发者们，来到关于使用计算机强大功能进行文本提取的课程，即光学字符识别（OCR）。如果你想无需支付昂贵的软件或在线服务，就能从图像中提取文本，那么这门课程适合你。你将学习如何用Python构建自己的OCR程序。EasyOCR让人工智能变得触手可及，只需几行代码即可实现。该工具提供了方便的方法，帮助我们轻松地从图像中提取文本，仿佛制作派一样简单，无需复杂的技术。 EasyOCR还提供了使用计算机图形处理单元（GPU）或中央处理单元（CPU）来提取图像的选项。在本课程中，我们将利用EasyOCR这个Python库，在只需几行代码的情况下，从图像中提取文本。此外，我们还将学习使用OpenCV的一些计算机视觉方法，以帮助在图像上叠加文本，为特定区域或边界框内的文本打标签。 无论你是出于个人还是商业目的，加入这门课程，掌握图像文本提取的技能吧！
Hello future developers, welcome to the course on text extraction using the power of computers, thus Optical Character Recognition( OCR).Do you want to extract text from an image for personal or commercial purposes without having to pay for expensive software or online services? This course is for you if you answered, Yes because, you will learn to build your very own OCR program in python.With EasyOCR, the power of artificial intelligence is just a python code away(a few lines of code).EasyOCR, comes with great methods that will help us extract text from images as easily as making pie without the need for sophisticated technologies.EasyOCR comes with options to other use the Graphical Processing Unit (GPU) of their computer or coders can use the normal Central Processing Unit (CPU) of their computers to extract images from images fed to the code.In this course, we will use easyOCR, a python package that can help us to extract texts from images with just a few lines of code.We will learn to use some computer vision methods from openCV to help us overlay text on our images, kinda tagging our text based on a region/ bounding box for which a particular text is located on an image.
