[{"data":1,"prerenderedAt":63},["ShallowReactive",2],{"docs-en-/en/docs/translator/translate-scanned-pdf":3},{"id":4,"title":5,"body":6,"description":55,"extension":56,"meta":57,"navigation":58,"path":59,"seo":60,"stem":61,"__hash__":62},"docs/en/docs/translator/translate-scanned-pdf.md","Translate Scanned PDFs",{"type":7,"value":8,"toc":50},"minimark",[9,13,17,20,27,32,40,47],[10,11,5],"h1",{"id":12},"translate-scanned-pdfs",[14,15,16],"p",{},"Doco Translate includes OCR for parsing and translating scanned PDFs.",[14,18,19],{},"In a scanned PDF, each page is usually stored as an image instead of structured text. Because text cannot be extracted directly, OCR must first recognize and extract the text before it can be translated.",[14,21,22],{},[23,24],"img",{"alt":25,"src":26},"OCR translation for scanned PDFs","/images/docs/scanned-pdf-ocr.webp",[28,29,31],"h2",{"id":30},"important-notes","Important Notes",[14,33,34,35,39],{},"Scanned documents are recognized visually and do not contain original text metadata that can help identify the language. If the source language is set to ",[36,37,38],"strong",{},"Auto Detect",", text recognition and extraction may be less accurate.",[14,41,42,43,46],{},"The best practice for scanned documents is to ",[36,44,45],{},"choose the source language manually",". Selecting the correct language improves both text extraction and OCR accuracy.",[14,48,49],{},"When Doco Translate detects a scanned document, it also prompts you to choose the source language manually to improve OCR and translation results.",{"title":51,"searchDepth":52,"depth":52,"links":53},"",2,[54],{"id":30,"depth":52,"text":31},"Use the built-in OCR in Doco Translate to parse and translate scanned PDF documents.","md",{},true,"/en/docs/translator/translate-scanned-pdf",{"title":5,"description":55},"en/docs/translator/translate-scanned-pdf","shUeIgToxa3sk2j20ywC1g0J2T5dP5JkpICRF5rx5OM",1787207634191]