This commit is contained in:
19
docs/snippets/elixir/ocr/image_preprocessing.md
Normal file
19
docs/snippets/elixir/ocr/image_preprocessing.md
Normal file
@@ -0,0 +1,19 @@
|
||||
```elixir title="Elixir"
|
||||
config_json = Jason.encode!(%{
|
||||
"ocr" => %{
|
||||
"backend" => "tesseract",
|
||||
"tesseract_config" => %{
|
||||
"preprocessing" => %{
|
||||
"target_dpi" => 300,
|
||||
"denoise" => true,
|
||||
"deskew" => true,
|
||||
"contrast_enhance" => true,
|
||||
"binarization_method" => "otsu"
|
||||
}
|
||||
}
|
||||
}
|
||||
})
|
||||
|
||||
{:ok, result} = Kreuzberg.extract_file_sync("scanned.pdf", "application/pdf", config_json)
|
||||
IO.puts(result.content)
|
||||
```
|
||||
Reference in New Issue
Block a user