From the course: AI Services and Google Distributed Cloud (GDC) Deployments and Operations by Google

Unlock this course with a free trial

Join today to access over 25,300 courses taught by industry experts.

Optical character recognition (OCR)

Optical character recognition (OCR)

- [Instructor] In this lesson, you'll learn about the OCR feature of Vertex AI, which detects typed text in a photo image or handwritten text. The OCR pre-trained API detects and transcribes text from handwriting and from PDF, TIFF, JPG, and PNG files. Data is returned in JSON format and includes page, block, paragraph, word, and break information. Responses can be stored in a database. For analysis, you must store files locally in the GDC environment. You can't use files hosted in Google Cloud storage or files that are publicly available for text detection. The primary difference between vision technology on GDC versus Google Cloud is that Google Cloud vision supports image, facial, and crop hint recognition, while vision on GDC only supports OCR. For OCR 46 languages are supported with 24 more in experimental mode. The text recognition feature has three categories of language support. Supported languages are…

Contents