Google Cloud Vision AI

The product is a computer vision platform that provides APIs and tools to analyze images, documents, and videos for tasks such as object detection, image labeling, OCR, and content moderation. It is for developers and data teams in businesses and government organizations that need to automate visual data processing and extract insights. It is delivered as managed cloud APIs including pre-trained models and no-code custom model training with pay-per-use billing.

Key features

• Image labeling via API
• Face and landmark detection
• Optical character recognition (OCR)
• Explicit content tagging (SafeSearch)
• Image generation from text prompts
• Image editing with text prompts
• Image-to-text description
• Subject model fine-tuning
• Extract text and data from documents
• Classify, split and extract document data
• Recognize objects, places, actions in video
• Video content moderation and analysis
• Custom model training with no-code tools