Last active
November 14, 2023 14:37
-
-
Save BenniG123/42b645e82b9f850d60735bbffbae339f to your computer and use it in GitHub Desktop.
Quick powershell script to grab all images in a folder, run tessaract OCR on all of them, and then pipe all output to out.txt
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
function Get-DirectoryName($initialDirectory) | |
{ | |
[System.Reflection.Assembly]::LoadWithPartialName("System.Windows.Forms") | Out-Null | |
$openFolderDialog = New-Object System.Windows.Forms.FolderBrowserDialog | |
$openFolderDialog.ShowDialog() | Out-Null | |
return $openFolderDialog.SelectedPath | |
} | |
Write-Output "Select image folder" | |
$folderPath = Get-DirectoryName -initialDirectory "~" | |
Write-Output "Selected $folderPath" | |
$files = Get-ChildItem "$folderPath\*" -Include *.png,*.jpg,*.bmp | |
$outFilePath = Join-Path $folderPath "out.txt" | |
foreach ($file in $files) | |
{ | |
$imagePath = Join-Path $folderPath $file.Name | |
$txtFileName = $file.BaseName | |
$txtPath = Join-Path $folderPath $txtFileName | |
Write-Output "$imagePath $txtPath" | |
# Actually do OCR - You have to add tesseract to your PATH, or specify its full path here | |
tesseract $imagePath $txtPath | |
# tesseract adds .txt to out files | |
$txtPath = $txtPath + ".txt" | |
# Write to single out file | |
$txtPath | Out-File $txtPath -Append -Encoding ascii | |
Get-Content $txtPath | Out-File $outFilePath -Append | |
Remove-Item $txtPath | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Thanks, I appreciate it.