Microsoft Azure Cognitive Services: Video Indexer API
By Alan Smith
Course info
Course info
Description
Azure Cognitive Services provides powerful artificial intelligence functionality as a service. Cognitive Services Video Indexer leverages Azure Cognitive Services to implement the analysis and interpretation of video and audio content. This course, Microsoft Azure Cognitive Services: Video Indexer API, explores the functionality of the Video Indexer API to programmatically automate the processing of media assets using the Video Indexer service with C# and Python. First, you’ll explore authentication and authorization using API keys to retrieve access tokens, along with the use of access tokens to call service methods. Next, you’ll focus on the indexing of content and how to effectively process a large number of media assets. Searching and playing content using the API will also be covered, allowing the Video Indexer to be integrated with web sites and applications. Finally, you’ll examine how to edit and correct audio transcripts, along with the use of language translation to provide closed captions to audiences in different regions. By the end of this course, you’ll have a working knowledge of how to harness the power of Azure Cognitive Services for video and audio analysis.
About the author
Alan Smith is a Windows Azure developer, trainer, mentor and evangelist at Active Solution in Stockholm. He has a strong hands-on philosophy and focusses on embracing the power and flexibility of cloud computing to deliver engaging and exciting demos.
More from the author
Section Introduction Transcripts
Course Overview
Hello, and welcome to my Pluralsight course, Microsoft Azure Cognitive Services: Video Indexer API. My name is Alan Smith, and I work as a consultant for Active Solution based in Stockholm, Sweden. In this course, we're going to be gaining an understanding of using the Azure Cognitive Services Video Indexer through the API, which will allow us to automate the processing and indexing of video and audio media assets. We'll start out by taking a quick look at the features of the Video Indexer, looking at how transcriptions can be generated along with identifying keywords, and topics, and sentiments on the media that we're indexing. We'll look at some of the most sophisticated features such as celebrity identification, face detection, and scene analysis. We'll look in detail about how we can use the API to utilize this functionality, focusing on how we can authenticate with the service and call the various methods. We'll be demonstrating how to call the API using both C# and Python. The requirements for the course, you should have some knowledge of C# or Python programming, and you will need to have access to a Video Indexer account. At the time of recording the course, there are free trials that you can sign up for. For some of the demos, an Azure subscription will be required in order to store the media that we're going to be indexing in Blob Storage.