Skip to Main Content
AI Services: Introduction to OCI Vision

About This Workshop

Youtube Video

About This Workshop
Enterprise image and document data has significant value related to core business activities and their customers. To gain business and customer insights effectively and at scale from this data, vision capabilities are needed. For example, identifying key requirements to understand customer perception of their products to address gaps. Some core capabilities include classifying images & documents, detecting objects, text & languages and extracting table information from the data. These capabilities are typically machine learning algorithms custom built, tuned by Data Scientists and productized for use in applications. Doing this is a time consuming and expensive proposition.

OCI Vision Service reduces time and effort to perform Vision tasks like image classification, object detection, text detection, document AI etc by providing key vision capabilities via production-ready REST APIs. The service enables applications to automate sophisticated image and document analysis at scale without needing ML expertise. The service functionality is implemented with pre-trained ML models which are often useful. They may also be further customized to understand the patterns of the customer’s context by providing additional data.

Workshop Info

1 hour
  • Introduction: OCI Vision
  • Lab 1: Use Vision Service through the OCI Console
  • Lab 2: Create a custom model through the OCI Console
  • Lab 3: Access OCI Vision in DataScience Notebook Session
  • Familiar with OCI Policy and SDK setup.
  • Familiar with Python programming for SDK usage is strongly recommended.
  • Familiar with OCI services DataScience is recommended, but not required.

Other Workshops you might like