About Google Cloud Vision Api
Google Cloud Vision API is a REST and RPC API that applies machine learning to images for label detection, face detection, OCR, logo detection, object localization, web entity detection, and explicit content filtering. Pricing is per-feature per image with the first 1,000 units free per month. It also supports AutoML Vision for training custom image classification models. New Google Cloud customers receive $300 in free credits.
AI Agent Use Cases
- Label and object detection
- Optical character recognition (OCR) including handwriting
- Face and landmark detection
- Logo and brand detection
- Safe search and explicit content detection
- AutoML Vision for custom model training
Available Actions
These are the specific actions that AI agents can perform with this tool
Annotate Images
1 input
Run image detection and annotation for a batch of images.
Asynchronous File Annotation
2 inputs
Perform asynchronous image detection and annotation for files like PDFs.
Cancel Vision Operation
1 input
Request to cancel a long-running Cloud Vision operation
Detect Labels in Image
1 input
Detects and returns descriptive labels identifying objects, entities, and concepts within a local or remote image.
Detect Logos in Image
Detects and identifies brand logos present in a local or remote image using Google Cloud Vision API.
Detect Text in Image
Extracts and identifies text content from images provided locally or via a URL using OCR technology.
Get Operation Status
2 inputs
Retrieve the latest state of a long-running operation using its unique name
Project Files Annotation
2 inputs
Perform image detection and annotation for a batch of files in a specified project.