|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/computer-vision-projects-with-python-in-4-hours/
课程评论：没有评论
课程名称：计算机视觉项目与Python，4小时速成！ 课程概述：Python编程语言是一种理想的平台，用于快速原型开发和生产级图像处理及计算机视觉代码。凭借其强大的语法和丰富的强大库，Python使得现代计算机视觉和机器学习技术对各种背景的开发者皆可访问。本课程采用实践导向的教学方式，旨在教授开发Python计算机视觉解决方案所需的技能。课程一开始，您将学习如何为主流操作系统设置Anaconda Python，并安装用于计算机视觉的前沿第三方库。随后，您将看到如何使用谷歌的Tesseract软件从真实图像中读取车牌文字，以及如何在TensorFlow中使用“DeeperCut”跟踪人体姿态。课程结束时，您将对计算机视觉的基本工具有全面的了解，并能够将其付诸实践。 课程内容与概述：本培训项目包含两个完整的课程，旨在提供最全面的培训。 第一个课程“Python 3计算机视觉项目”开始于教您如何为主要操作系统（Windows、Mac和Linux）设置Anaconda Python，并与强大的计算机视觉和机器学习工具OpenCV、TensorFlow及Dlib结合。您将学习最先进的图像分类技术以及如何在视频中找到并识别人体。课程中将引导您完成手写数字分类器，检测面部特征，并最终开发一个通用图像分类器。课程结束时，您将掌握计算机视觉的基本工具并能加以应用。 第二个课程“高级计算机视觉项目”将为您提供利用最新计算机视觉算法的工具和技能，使您能够制作出过去无法实现的应用。在此课程中，您将继续使用TensorFlow，并扩展生成图像的完整描述。随后，您将学习如何使用谷歌的Tesseract软件从真实图像中读取车牌文字，并查看如何在TensorFlow中使用“DeeperCut”跟踪人体姿态。课程结束时，您将开发一个能够估计图像中人体姿势的应用，并能够采用最佳实践进行计算机视觉和机器学习。 作者介绍：Matthew Rever是一位在国家实验室工作的图像处理和计算机视觉工程师。拥有多年自动化分析复杂科学数据的经验，以及控制复杂仪器的经验。他应用计算机视觉技术有效地节省了大量宝贵的人力资源，同时他也热衷于将计算机视觉的最新进展推广给各类开发者。
The Python programming language is an ideal platform for rapidly prototyping and developing production-grade codes for image processing and computer vision with its robust syntax and wealth of powerful libraries. Python's wealth of powerful packages along with its clear syntax make state-of-the art computer vision and machine learning accessible to developers with a variety of backgrounds. This is a hands-on, practical approach, designed to teach you the skills required to develop computer vision solutions in Python. At the very beginning you will learn how to set up Anaconda Python for the major OS's with cutting-edge third-party libraries for computer vision. Than you'll see how to read text from license plates from real-world images using Google's Tesseract Software & how to track human body poses using "DeeperCut" within TensorFlow. By end of this course, you'll know the complete insight into basic tools of computer vision and be able to put it into practice.Contents and OverviewThis training program includes 2 complete courses, carefully chosen to give you the most comprehensive training possible.The first course, Computer Vision Projects with Python 3 start by showing you how to set up Anaconda Python for the major OSes with cutting-edge third-party libraries for computer vision. You'll learn state-of-the-art techniques to classify images and find and identify humans within videos. Next, you'll understand how to set up Anaconda Python 3 for the major OSes (Windows, Mac, and Linux) and augment it with the powerful vision and machine learning tools OpenCV and TensorFlow, as well as Dlib. You'll be taken through the handwritten digits classifier and then move on to detecting facial features and finally develop a general image classifier. By the end of this course, you'll know the basic tools of computer vision and be able to put it into practice.The second course, Advanced Computer Vision Projects will equip you with the tools and skills to utilize the latest and greatest algorithms in computer vision, making applications that weren't possible until recent years. In this course, you'll continue to use TensorFlow and extend it to generate full captions from images. Later, you'll see how to read text from license plates from real-world images using Google's Tesseract Software. Finally, you'll see how to track human body poses using "DeeperCut" within TensorFlow. At the end of this course, you'll develop an application that can estimate human poses within images and will be able to take on the world with best practices in computer vision with machine learning.About the Authors:Matthew Rever is an image processing and computer vision engineer at a major national laboratory. He has years of experience automating the analysis of complex scientific data, as well as the control of sophisticated instruments. He has applied computer vision technology to save a great many hours of valuable human labor. He is also enthusiastic about making the latest developments in computer vision accessible to developers of all backgrounds.
