How to Extract Amharic Text from a Photo or Scan (OCR)
A scanned document or photo is only an image, so you cannot select or search its text. OCR reads the letters and converts them to text.
What is OCR?
OCR reads the letters in an image and turns them into text you can select and search. After OCR, a scanned letter, a book page or a photographed document can be copied, edited and searched.
How to extract Amharic text from an image
Everything runs in your browser, so your images are not uploaded.
- Open the Amharic OCR tool.
- Load the image.
- Choose Amharic, or Amharic and English if both appear.
- Copy or download the result.
Extracting text from a scanned PDF
For a scanned PDF, use Amharic PDF OCR, which can read up to 30 pages at a time. If your PDF already contains real text, you do not need OCR: use PDF to Text. To bring the text into Word, read how to convert PDF to Word.
How to get better results
- Use a flat, well-lit photo and avoid shadows.
- Hold the camera directly above the page so the text is straight.
- A high-quality scan beats a blurry photo.
- Printed text is read far better than handwriting.
Always check the result
OCR is not perfect. Compare names, numbers and dates with the original and fix visible mistakes before you send the text. Your images run in your browser, so they are not uploaded.
Frequently asked questions
Is Amharic OCR free?
Yes. The tool is free and runs in your browser.
Can it read handwriting?
Printed text is read much better. Results for handwriting are often poor, so check them carefully.
How many pages can I read at once?
Amharic PDF OCR reads up to 30 pages at a time.