|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/introduction-to-vision-ai/
课程评论：没有评论
课程名称：视觉人工智能导论 课程概述：本课程的主要目标包括以下几个关键主题：描述视觉人工智能的体验，覆盖包含许多真实和假设使用案例的视觉人工智能用例库，使用两个视觉人工智能案例研究解释视觉人工智能体验，最终您将能够理解视觉人工智能解决方案的组成部分。该课程分为多个部分。 第1部分提供课程介绍，包括课程大纲、目标受众、预期成果以及课程作者。 第2部分将描述什么是视觉人工智能，以及它如何用于对各种图像和视频进行分类和归档。我们将涵盖视觉人工智能的关键概念及其五个复杂性级别。 第3部分将针对文档理解、场景分析、实体识别和图像生成四个不同类别进行一系列用例展示，展示与上述类别相关的不同用例及其背后使用的各种视觉概念。 第4部分将为您介绍视觉人工智能背后的关键技术，如深度学习、计算机视觉模型（如CNN、RNN和Faster R-CNN）、迁移学习及流行库VGG-16和嵌入，以及开源计算机视觉库Keras。 第5部分将介绍第一个视觉人工智能的良好示例，以分析支付保护计划，解释薪资表格。美国政府为支持因COVID而受到经济影响的小型企业发布了超过1万亿美元。由于小企业申请数量猛增，需要自动提取申请表中的薪资信息，而这些表格中的许多是手工填写的。我们将描述该问题、解决方案组件和此问题的效益案例。 第6部分将介绍针对零售/仓库的第二个案例研究，即图像分类和物品识别。我们将描述该问题、用户角色、解决方案组件和此问题的效益案例。 最后一部分将总结课程内容，并介绍该领域的几个商业产品。我们还将讨论相关参考资料和后续课程，以帮助您进一步学习视觉人工智能。
Key objectives of the course include following key topics: Describe Vision AI experienceCover Vision AI Use case Library containing many real and hypothetical use cases of Vision AIExplain Vision AI experience using 2 Vision AI case studiesFinally, you will be able to Understand components of a Vision AI solutionThis course is divided into multiple sections.Section 1 provides an introduction to the course including course outline, audience, expected outcome, and authors for the course.In section 2, we will describe what is a Vision AI and how it is being used in classifying and cataloging various image and videos. We will cover key concepts behind Vision VI and its 5 complexity levels'In section 3, we will take a series of use cases in four different categories likeDocument UnderstandingScene AnalysisEntity RecognitionImage generationand will show you different use cases associated with above categories where different vision concepts are employed.In Section 4, we will introduce you to key technologies behind Vision AI like Deep LearningComputer Vision models like CNN, RNN and Faster R-CNNTransfer Learning and popular library VGG-16EmbeddingComputer Vision open-source library KerasIn Section 5, we will cover first good example of Vision AI for analyzing Payment protection Plan to interpret payroll forms. US Government released more than 1 trillion dollars to support small businesses economically impacted by COVID. As small business applications grew, there was need for automated extraction of payroll information from applicant forms, many of which were filled by hand. We will describe problem, solution components and benefit case for this problem.In section 6, we will introduce second case study on Image Classification and Item Identification for Retail/warehouse outlets, We will describe problem, user persona, solution components and benefit case for this problem.In the last section, we will summarize the course contents and will introduce several commercial offerings in this area. We will also discuss related references and courses to move forward with your Vision AI learning.
