@slates-integrations/google-cloud-vision
v0.2.0-rc.3
Published
Analyze images using pre-trained machine learning models. Detect and label objects, faces, landmarks, logos, and text (OCR) in images. Extract text from photos, documents, PDFs, and handwritten content. Detect explicit or unsafe content with SafeSearch. I
Readme
Google Cloud Vision
Analyze images using pre-trained machine learning models. Detect and label objects, faces, landmarks, logos, and text (OCR) in images. Extract text from photos, documents, PDFs, and handwritten content. Detect explicit or unsafe content with SafeSearch. Identify dominant colors and image properties. Localize multiple objects with bounding regions. Get crop hints for optimal image framing. Detect web entities and find visually similar images online. Supports base64-encoded images, Cloud Storage URIs, and public URLs. Run asynchronous batch annotation on up to 2000 images.
License
This integration is licensed under the FSL-1.1.
