Translating PDFs with scanned image content is a highly requested feature from Document translation customers. Document translation is enterprise-ready with Azure Active Directory authentication, providing secured access between the service and storage through Managed Identity. Document translation supports a variety of file types, including Word, PowerPoint and PDF, and customers can use either pre-built or custom machine translation models. It’s worth noting that the quality of the translation may vary depending on the quality of the image and the language of the text.Today, the Document translation feature of Translator, a Microsoft Azure Cognitive Service, adds the ability to translate PDF documents containing scanned image content, eliminating the need for customers to preprocess them through an OCR engine before translation.ĭocument translation was made generally available last year, May 25, 2021, allowing customers to translate entire documents and batches of documents into more than 110 languages and dialects while preserving the layout and formatting of the original file. Using the Cloud-based services: You can use the Cloud-based OCR services like Google Cloud Vision OCR, Microsoft Azure OCR, Amazon Textract etc to extract the text from image and then use cloud-based translation services like Google Translate API, Microsoft Translator Text API etc to translate the text. Using a software on your computer: Some software like Adobe Acrobat Pro, ABBYY FineReader or Microsoft OneNote allow you to extract text from an image and then you can use built-in or external tools for translation. Using online OCR (Optical Character Recognition) tools: Websites like Online OCR and Free OCR allow you to upload an image of text and convert it to editable text, which can then be translated using a separate translation tool. Using a mobile app: Many translation apps, such as Google Translate, allow you to take a photo of the text and translate it within the app. There are several ways to translate text from an image, including:
0 kommentar(er)
