Build an Application That Can “See” and “Understand” Visual Data

Introduction

Oracle Cloud Infrastructure (OCI) Vision unlocks image intelligence. Pretrained models can handle common tasks, such as finding objects in images and extracting text from documents. You can also train custom models for specific needs—for example, a retailer identifying clothing types. These features, along with easy integration, make OCI Vision a powerful tool for developers to build applications that can process visual data.

This solution will guide you through building a basic application in Oracle JavaScript Extension Toolkit (JET) using the virtual DOM (VDOM) architecture and integrating OCI Vision services for enhanced functionality.

Demo

<

Prerequisites and setup

1. Oracle Cloud account—sign-up page
2. OCI Generative AI—documentation
3. OCI Vision—documentation
4. Oracle JET—resource page

Getting started

• Detailed steps and sample code on GitHub

Additional resources

• Blog: Oracle JET with VDOM and OCI Vision
• Architecture: Use OCI Vision to extract data from images and scanned documents