오토핫키(AutoHotkey) 광학 문자 인식(OCR) - UWP API 2배 빠름

 

 

UWP API를 사용한 OCR 광학 문자 인식입니다.

원문 주소 : https://www.autohotkey.com/boards/viewtopic.php?t=72674

UWP API 참고 주소 : https://learn.microsoft.com/en-us/uwp/api/windows.media.ocr?view=winrt-22621

Windows.Media.Ocr Namespace - Windows UWP applications

 

UWP

UWP(Universal Windows Platform)은 Microsoft가 개발한 응용 프로그램 플랫폼입니다. UWP의 주요 목표는 Windows 운영 체제를 사용하는 모든 장치에서 실행되는 응용 프로그램을 쉽게 개발할 수 있도록 하는 것입니다.

이를 통해 개발자는 한 번의 코드 작성으로 PC, 태블릿, 스마트폰, Xbox, HoloLens 등

다양한 장치에서 동일한 응용 프로그램을 실행할 수 있습니다.

 

 

msgbox % ocr("ShowAvailableLanguages")
msgbox % ocr("test.jpg", "en")
msgbox % ocr("test.jpg", "ru")
msgbox % ocr("test.jpg")
ExitApp

ocr(file, lang := "FirstFromAvailableLanguages")
{
   static OcrEngineStatics, OcrEngine, MaxDimension, LanguageFactory, Language, CurrentLanguage, BitmapDecoderStatics, GlobalizationPreferencesStatics
   if (OcrEngineStatics = "")
   {
      CreateClass("Windows.Globalization.Language", ILanguageFactory := "{9B0252AC-0C27-44F8-B792-9793FB66C63E}", LanguageFactory)
      CreateClass("Windows.Graphics.Imaging.BitmapDecoder", IBitmapDecoderStatics := "{438CCB26-BCEF-4E95-BAD6-23A822E58D01}", BitmapDecoderStatics)
      CreateClass("Windows.Media.Ocr.OcrEngine", IOcrEngineStatics := "{5BFFA85A-3384-3540-9940-699120D428A8}", OcrEngineStatics)
      DllCall(NumGet(NumGet(OcrEngineStatics+0)+6*A_PtrSize), "ptr", OcrEngineStatics, "uint*", MaxDimension)   ; MaxImageDimension
   }
   if (file = "ShowAvailableLanguages")
   {
      if (GlobalizationPreferencesStatics = "")
         CreateClass("Windows.System.UserProfile.GlobalizationPreferences", IGlobalizationPreferencesStatics := "{01BF4326-ED37-4E96-B0E9-C1340D1EA158}", GlobalizationPreferencesStatics)
      DllCall(NumGet(NumGet(GlobalizationPreferencesStatics+0)+9*A_PtrSize), "ptr", GlobalizationPreferencesStatics, "ptr*", LanguageList)   ; get_Languages
      DllCall(NumGet(NumGet(LanguageList+0)+7*A_PtrSize), "ptr", LanguageList, "int*", count)   ; count
      loop % count
      {
         DllCall(NumGet(NumGet(LanguageList+0)+6*A_PtrSize), "ptr", LanguageList, "int", A_Index-1, "ptr*", hString)   ; get_Item
         DllCall(NumGet(NumGet(LanguageFactory+0)+6*A_PtrSize), "ptr", LanguageFactory, "ptr", hString, "ptr*", LanguageTest)   ; CreateLanguage
         DllCall(NumGet(NumGet(OcrEngineStatics+0)+8*A_PtrSize), "ptr", OcrEngineStatics, "ptr", LanguageTest, "int*", bool)   ; IsLanguageSupported
         if (bool = 1)
         {
            DllCall(NumGet(NumGet(LanguageTest+0)+6*A_PtrSize), "ptr", LanguageTest, "ptr*", hText)
            buffer := DllCall("Combase.dll\WindowsGetStringRawBuffer", "ptr", hText, "uint*", length, "ptr")
            text .= StrGet(buffer, "UTF-16") "`n"
         }
         ObjRelease(LanguageTest)
      }
      ObjRelease(LanguageList)
      return text
   }
   if (lang != CurrentLanguage) or (lang = "FirstFromAvailableLanguages")
   {
      if (OcrEngine != "")
      {
         ObjRelease(OcrEngine)
         if (CurrentLanguage != "FirstFromAvailableLanguages")
            ObjRelease(Language)
      }
      if (lang = "FirstFromAvailableLanguages")
         DllCall(NumGet(NumGet(OcrEngineStatics+0)+10*A_PtrSize), "ptr", OcrEngineStatics, "ptr*", OcrEngine)   ; TryCreateFromUserProfileLanguages
      else
      {
         CreateHString(lang, hString)
         DllCall(NumGet(NumGet(LanguageFactory+0)+6*A_PtrSize), "ptr", LanguageFactory, "ptr", hString, "ptr*", Language)   ; CreateLanguage
         DeleteHString(hString)
         DllCall(NumGet(NumGet(OcrEngineStatics+0)+9*A_PtrSize), "ptr", OcrEngineStatics, ptr, Language, "ptr*", OcrEngine)   ; TryCreateFromLanguage
      }
      if (OcrEngine = 0)
      {
         msgbox Can not use language "%lang%" for OCR, please install language pack.
         ExitApp
      }
      CurrentLanguage := lang
   }
   if (SubStr(file, 2, 1) != ":")
      file := A_ScriptDir "\" file
   if !FileExist(file) or InStr(FileExist(file), "D")
   {
      msgbox File "%file%" does not exist
      ExitApp
   }
   VarSetCapacity(GUID, 16)
   DllCall("ole32\CLSIDFromString", "wstr", IID_RandomAccessStream := "{905A0FE1-BC53-11DF-8C49-001E4FC686DA}", "ptr", &GUID)
   DllCall("ShCore\CreateRandomAccessStreamOnFile", "wstr", file, "uint", Read := 0, "ptr", &GUID, "ptr*", IRandomAccessStream)
   DllCall(NumGet(NumGet(BitmapDecoderStatics+0)+14*A_PtrSize), "ptr", BitmapDecoderStatics, "ptr", IRandomAccessStream, "ptr*", BitmapDecoder)   ; CreateAsync
   WaitForAsync(BitmapDecoder)
   BitmapFrame := ComObjQuery(BitmapDecoder, IBitmapFrame := "{72A49A1C-8081-438D-91BC-94ECFC8185C6}")
   DllCall(NumGet(NumGet(BitmapFrame+0)+12*A_PtrSize), "ptr", BitmapFrame, "uint*", width)   ; get_PixelWidth
   DllCall(NumGet(NumGet(BitmapFrame+0)+13*A_PtrSize), "ptr", BitmapFrame, "uint*", height)   ; get_PixelHeight
   if (width > MaxDimension) or (height > MaxDimension)
   {
      msgbox Image is to big - %width%x%height%.`nIt should be maximum - %MaxDimension% pixels
      ExitApp
   }
   BitmapFrameWithSoftwareBitmap := ComObjQuery(BitmapDecoder, IBitmapFrameWithSoftwareBitmap := "{FE287C9A-420C-4963-87AD-691436E08383}")
   DllCall(NumGet(NumGet(BitmapFrameWithSoftwareBitmap+0)+6*A_PtrSize), "ptr", BitmapFrameWithSoftwareBitmap, "ptr*", SoftwareBitmap)   ; GetSoftwareBitmapAsync
   WaitForAsync(SoftwareBitmap)
   DllCall(NumGet(NumGet(OcrEngine+0)+6*A_PtrSize), "ptr", OcrEngine, ptr, SoftwareBitmap, "ptr*", OcrResult)   ; RecognizeAsync
   WaitForAsync(OcrResult)
   DllCall(NumGet(NumGet(OcrResult+0)+6*A_PtrSize), "ptr", OcrResult, "ptr*", LinesList)   ; get_Lines
   DllCall(NumGet(NumGet(LinesList+0)+7*A_PtrSize), "ptr", LinesList, "int*", count)   ; count
   loop % count
   {
      DllCall(NumGet(NumGet(LinesList+0)+6*A_PtrSize), "ptr", LinesList, "int", A_Index-1, "ptr*", OcrLine)
      DllCall(NumGet(NumGet(OcrLine+0)+7*A_PtrSize), "ptr", OcrLine, "ptr*", hText) 
      buffer := DllCall("Combase.dll\WindowsGetStringRawBuffer", "ptr", hText, "uint*", length, "ptr")
      text .= StrGet(buffer, "UTF-16") "`n"
      ObjRelease(OcrLine)
   }
   Close := ComObjQuery(IRandomAccessStream, IClosable := "{30D5A829-7FA4-4026-83BB-D75BAE4EA99E}")
   DllCall(NumGet(NumGet(Close+0)+6*A_PtrSize), "ptr", Close)   ; Close
   ObjRelease(Close)
   Close := ComObjQuery(SoftwareBitmap, IClosable := "{30D5A829-7FA4-4026-83BB-D75BAE4EA99E}")
   DllCall(NumGet(NumGet(Close+0)+6*A_PtrSize), "ptr", Close)   ; Close
   ObjRelease(Close)
   ObjRelease(IRandomAccessStream)
   ObjRelease(BitmapDecoder)
   ObjRelease(BitmapFrame)
   ObjRelease(BitmapFrameWithSoftwareBitmap)
   ObjRelease(SoftwareBitmap)
   ObjRelease(OcrResult)
   ObjRelease(LinesList)
   return text
}



CreateClass(string, interface, ByRef Class)
{
   CreateHString(string, hString)
   VarSetCapacity(GUID, 16)
   DllCall("ole32\CLSIDFromString", "wstr", interface, "ptr", &GUID)
   result := DllCall("Combase.dll\RoGetActivationFactory", "ptr", hString, "ptr", &GUID, "ptr*", Class)
   if (result != 0)
   {
      if (result = 0x80004002)
         msgbox No such interface supported
      else if (result = 0x80040154)
         msgbox Class not registered
      else
         msgbox error: %result%
      ExitApp
   }
   DeleteHString(hString)
}

CreateHString(string, ByRef hString)
{
    DllCall("Combase.dll\WindowsCreateString", "wstr", string, "uint", StrLen(string), "ptr*", hString)
}

DeleteHString(hString)
{
   DllCall("Combase.dll\WindowsDeleteString", "ptr", hString)
}

WaitForAsync(ByRef Object)
{
   AsyncInfo := ComObjQuery(Object, IAsyncInfo := "{00000036-0000-0000-C000-000000000046}")
   loop
   {
      DllCall(NumGet(NumGet(AsyncInfo+0)+7*A_PtrSize), "ptr", AsyncInfo, "uint*", status)   ; IAsyncInfo.Status
      if (status != 0)
      {
         if (status != 1)
         {
            DllCall(NumGet(NumGet(AsyncInfo+0)+8*A_PtrSize), "ptr", AsyncInfo, "uint*", ErrorCode)   ; IAsyncInfo.ErrorCode
            msgbox AsyncInfo status error: %ErrorCode%
            ExitApp
         }
         ObjRelease(AsyncInfo)
         break
      }
      sleep 10
   }
   DllCall(NumGet(NumGet(Object+0)+8*A_PtrSize), "ptr", Object, "ptr*", ObjectResult)   ; GetResults
   ObjRelease(Object)
   Object := ObjectResult
}

 

test.zip

0.00MB

 

 

 

이미지 ( JPG (JPEG), BMP , PNG , WEBG , webp 등 되는 것 같습니다.

이미지의 글자를 인식 및 추출 할 수있으며 ,

텍스트 글자의 갯수 및 종류, 키워드, 단어 등을 추출하여 만들 수있는 프로그램은 무궁무진 합니다.