OCR (Optical Character Recognition)

Powered by a foundational model, Document AI Custom Extractor extracts text and data from documents, generic and domain-specific, faster and with higher accuracy. Easily fine-tune with just 5-10 documents for even better performance.

 If you want to train your own model, auto-label your datasets with the foundational model for faster time to production.

You can also choose to use pre-trained specialized processors - see the full list of processors. 

Mr. Cooper is one of the largest home loan servicers in the country focused on delivering a variety of servicing and lending products, services and technologies to homeowners.

They built a container-based document processing pipeline with a modular architecture on Google’s OCR technology stack and achieved these results:

- Over 95% accuracy for critical documents.

- Peak throughput of 4000 pages/min, an average throughput of 2000 pages/min.

- Increased document processing efficiency by 400%.

Powered by GenAI, Document AI delivers great accuracy in extracting data from documents of varying layouts and quality. You can connect it with Cloud Storage so your unstructured documents have enterprise-grade compliance. BigQuery helps batch process and analyze the extracted data any way you like. With Looker, you can easily build visualizations based on your BigQuery tables. Vertex AI Search enables you to query and search your documents in Cloud Storage, conversationally or traditionally.

Image tagging is also referred to as image labeling. 

Cloud Vision API can identify and label general objects, landmarks, locations, logos, activities, animal species, products, and more in an image. Once the images are tagged with the detected labels, image search, processing and management are automated and easier.

If you need targeted custom labels, use Cloud AutoML to train a custom ML model.

To use Google OCR technologies on premise, use OCR On-Prem, available in the Cloud Marketplace.

To run a basic image processing pipeline that detects labels as shown on the right, your monthly cost would be $27.36.

You can check the usage assumptions made to arrive at this number in the pricing calculator.

First 1,000 units per month is free.

Using Cloud AutoML, researchers at Texas A&M University were able to custom train a multi-labeled dataset model with 10,458 shoreline images in 24 compute hours. The model helped the researchers predict and track shoreline changes with an average accuracy of 95.2%.

AutoML provided the added flexibility in training advanced models using the training images, letting the team inspect the data and analyze the results via an intuitive UI, and providing an API for scalable serving.

Through Cloud Vision API, you can detect and extract text and handwriting from any images in different languages. It also has multi-region support for which you can specify continent-level data storage and OCR processing.

You can choose to get immediate results for a small number of images (up to 16 per request), or batch process a larger number of images (up to 2000 per request) asynchronously for a result later.

To run a basic processing pipeline that extracts text from images as shown on the right, your monthly cost would be $27.36.

You can check the usage assumptions made to arrive at this number in the pricing calculator.

First 1,000 units per month is free.