Amazon Rekognition can detect and read text in an image or video, and return bounding boxes for each word found. On 11/17/2021, we launched support for 7 new languages in Amazon Rekognition text detection in images – Arabic, Russian, German, French, Italian, Portuguese and Spanish. Amazon Rekognition can automatically detect and extract text in images in all the supported languages, without requiring a language parameter as user input. In addition, Amazon Rekognition delivers higher overall accuracy, with improvements for vertical and curved text.

Categories: AWS