Google Vision AI allows you to derive insights from images uploaded into Google Cloud. The Google Cloud Vision API provides pre-trained machine learning models that can provide contextual data on those images. The models have been trained on a large number of images in order to recognize faces, geographic locations, and even explicit content such as violence.
The Google Cloud Vision API How-to Guides page contains a full list of detection features provided by the API. These powerful API calls can be utilized within a Google Cloud Function in order to integrate vision detection into your applications.
In this lab, you will develop two Google Cloud functions that detect popular landmarks and logos within a provided image.
Learning Objectives
Upon completion of this beginner level lab, you will be able to:
- Develop a Google Cloud Function that detects popular landmarks within an image
- Develop a Google Cloud Function that detects popular product logos within an image
Intended Audience
- Cloud Architects
- Machine Learning Engineers
Prerequisites
Familiarity with the following will be beneficial but is not required:
- Google Cloud Functions
The following content can be used to fulfill the prerequisite:
Jun is a Cloud Labs Developer with previous experience as a Software Engineer and Cloud Developer. He holds the AWS Certified Solutions Architect and DevOps Engineer Professional certifications. He also holds the AWS Certified Solutions Architect, Developer, and SysOps Administrator Associate certifications.
Jun is focused on giving back to the growing cloud community by sharing his knowledge and experience with students and creating engaging content.