AutoHotkey Community

Let's help each other out
https://www.autohotkey.com/boards/

Optical character recognition (OCR) with UWP API

https://www.autohotkey.com/boards/viewtopic.php?f=6&t=72674

Page 1 of 9

Optical character recognition (OCR) with UWP API

Posted: 19 Feb 2020, 20:58
by malcev
https://docs.microsoft.com/en-us/uwp/api/windows.media.ocr
API recognizes text in 2 ways.
1) By indicating the language directly
2) Takes the first from the list of installed languages by their priority and possibility for recognition.
msgbox % ocr("ShowAvailableLanguages") - shows this list (OCR will take the first language of it).
msgbox % ocr("test.jpg") - OCR will recognize with the language taken from the list.
msgbox % ocr("test.jpg", "en") - english.
msgbox % ocr("test.jpg", "ru")- russian.
2 languages simultaneously - no chance.

Code: Select all

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
}
Script for recognizing screenshots by teadrinker:

Code: Select all

#NoEnv
SetBatchLines, -1
Return

Esc:: ExitApp

^X::
hBitmap := HBitmapFromScreen(GetArea()*)
pIRandomAccessStream := HBitmapToRandomAccessStream(hBitmap)
DllCall("DeleteObject", "Ptr", hBitmap)
text := ocr(pIRandomAccessStream, "ru")
MsgBox, % text
Return

GetArea() {
   area := []
   StartSelection(area)
   while !area.w
      Sleep, 100
   Return area
}
   
StartSelection(area) {
   handler := Func("Select").Bind(area)
   Hotkey, LButton, % handler, On
   ReplaceSystemCursors("IDC_CROSS")
}

Select(area) {
   static hGui := CreateSelectionGui()
   Hook := new WindowsHook(WH_MOUSE_LL := 14, "LowLevelMouseProc", hGui)
   Loop {
      KeyWait, LButton
      WinGetPos, X, Y, W, H, ahk_id %hGui%
   } until w > 0
   ReplaceSystemCursors("")
   Hotkey, LButton, Off
   Hook := ""
   Gui, %hGui%:Show, Hide
   for k, v in ["x", "y", "w", "h"]
      area[v] := %v%
}

ReplaceSystemCursors(IDC = "")
{
   static IMAGE_CURSOR := 2, SPI_SETCURSORS := 0x57
        , exitFunc := Func("ReplaceSystemCursors").Bind("")
        , SysCursors := { IDC_APPSTARTING: 32650
                        , IDC_ARROW      : 32512
                        , IDC_CROSS      : 32515
                        , IDC_HAND       : 32649
                        , IDC_HELP       : 32651
                        , IDC_IBEAM      : 32513
                        , IDC_NO         : 32648
                        , IDC_SIZEALL    : 32646
                        , IDC_SIZENESW   : 32643
                        , IDC_SIZENWSE   : 32642
                        , IDC_SIZEWE     : 32644
                        , IDC_SIZENS     : 32645 
                        , IDC_UPARROW    : 32516
                        , IDC_WAIT       : 32514 }
   if !IDC {
      DllCall("SystemParametersInfo", UInt, SPI_SETCURSORS, UInt, 0, UInt, 0, UInt, 0)
      OnExit(exitFunc, 0)
   }
   else  {
      hCursor := DllCall("LoadCursor", Ptr, 0, UInt, SysCursors[IDC], Ptr)
      for k, v in SysCursors  {
         hCopy := DllCall("CopyImage", Ptr, hCursor, UInt, IMAGE_CURSOR, Int, 0, Int, 0, UInt, 0, Ptr)
         DllCall("SetSystemCursor", Ptr, hCopy, UInt, v)
      }
      OnExit(exitFunc)
   }
}

CreateSelectionGui() {
   Gui, New, +hwndhGui +Alwaysontop -Caption +LastFound +ToolWindow +E0x20 -DPIScale
   WinSet, Transparent, 130
   Gui, Color, FFC800
   Return hGui
}

LowLevelMouseProc(nCode, wParam, lParam) {
   static WM_MOUSEMOVE := 0x200, WM_LBUTTONUP := 0x202
        , coords := [], startMouseX, startMouseY, hGui
        , timer := Func("LowLevelMouseProc").Bind("timer", "", "")
   
   if (nCode = "timer") {
      while coords[1] {
         point := coords.RemoveAt(1)
         mouseX := point[1], mouseY := point[2]
         x := startMouseX < mouseX ? startMouseX : mouseX
         y := startMouseY < mouseY ? startMouseY : mouseY
         w := Abs(mouseX - startMouseX)
         h := Abs(mouseY - startMouseY)
         try Gui, %hGUi%: Show, x%x% y%y% w%w% h%h% NA
      }
   }
   else {
      (!hGui && hGui := A_EventInfo)
      if (wParam = WM_LBUTTONUP)
         startMouseX := startMouseY := ""
      if (wParam = WM_MOUSEMOVE)  {
         mouseX := NumGet(lParam + 0, "Int")
         mouseY := NumGet(lParam + 4, "Int")
         if (startMouseX = "") {
            startMouseX := mouseX
            startMouseY := mouseY
         }
         coords.Push([mouseX, mouseY])
         SetTimer, % timer, -10
      }
      Return DllCall("CallNextHookEx", Ptr, 0, Int, nCode, UInt, wParam, Ptr, lParam)
   }
}

class WindowsHook {
   __New(type, callback, eventInfo := "", isGlobal := true) {
      this.callbackPtr := RegisterCallback(callback, "Fast", 3, eventInfo)
      this.hHook := DllCall("SetWindowsHookEx", "Int", type, "Ptr", this.callbackPtr
                                              , "Ptr", !isGlobal ? 0 : DllCall("GetModuleHandle", "UInt", 0, "Ptr")
                                              , "UInt", isGlobal ? 0 : DllCall("GetCurrentThreadId"), "Ptr")
   }
   __Delete() {
      DllCall("UnhookWindowsHookEx", "Ptr", this.hHook)
      DllCall("GlobalFree", "Ptr", this.callBackPtr, "Ptr")
   }
}

HBitmapFromScreen(X, Y, W, H) {
   HDC := DllCall("GetDC", "Ptr", 0, "UPtr")
   HBM := DllCall("CreateCompatibleBitmap", "Ptr", HDC, "Int", W, "Int", H, "UPtr")
   PDC := DllCall("CreateCompatibleDC", "Ptr", HDC, "UPtr")
   DllCall("SelectObject", "Ptr", PDC, "Ptr", HBM)
   DllCall("BitBlt", "Ptr", PDC, "Int", 0, "Int", 0, "Int", W, "Int", H
                   , "Ptr", HDC, "Int", X, "Int", Y, "UInt", 0x00CC0020)
   DllCall("DeleteDC", "Ptr", PDC)
   DllCall("ReleaseDC", "Ptr", 0, "Ptr", HDC)
   Return HBM
}

HBitmapToRandomAccessStream(hBitmap) {
   static IID_IRandomAccessStream := "{905A0FE1-BC53-11DF-8C49-001E4FC686DA}"
        , IID_IPicture            := "{7BF80980-BF32-101A-8BBB-00AA00300CAB}"
        , PICTYPE_BITMAP := 1
        , BSOS_DEFAULT   := 0
        
   DllCall("Ole32\CreateStreamOnHGlobal", "Ptr", 0, "UInt", true, "PtrP", pIStream, "UInt")
   
   VarSetCapacity(PICTDESC, sz := 8 + A_PtrSize*2, 0)
   NumPut(sz, PICTDESC)
   NumPut(PICTYPE_BITMAP, PICTDESC, 4)
   NumPut(hBitmap, PICTDESC, 8)
   riid := CLSIDFromString(IID_IPicture, GUID1)
   DllCall("OleAut32\OleCreatePictureIndirect", "Ptr", &PICTDESC, "Ptr", riid, "UInt", false, "PtrP", pIPicture, "UInt")
   ; IPicture::SaveAsFile
   DllCall(NumGet(NumGet(pIPicture+0) + A_PtrSize*15), "Ptr", pIPicture, "Ptr", pIStream, "UInt", true, "UIntP", size, "UInt")
   riid := CLSIDFromString(IID_IRandomAccessStream, GUID2)
   DllCall("ShCore\CreateRandomAccessStreamOverStream", "Ptr", pIStream, "UInt", BSOS_DEFAULT, "Ptr", riid, "PtrP", pIRandomAccessStream, "UInt")
   ObjRelease(pIPicture)
   ObjRelease(pIStream)
   Return pIRandomAccessStream
}

CLSIDFromString(IID, ByRef CLSID) {
   VarSetCapacity(CLSID, 16, 0)
   if res := DllCall("ole32\CLSIDFromString", "WStr", IID, "Ptr", &CLSID, "UInt")
      throw Exception("CLSIDFromString failed. Error: " . Format("{:#x}", res))
   Return &CLSID
}


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
   }
   IRandomAccessStream := file
   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
}

Re: Optical character recognition (OCR) with UWP API

Posted: 19 Feb 2020, 23:15
by rommmcek
This is enormous!
Quickly tested on .bmp, .png, .gif and .jpg. Seems to be much more precise then tesseract!

Re: Optical character recognition (OCR) with UWP API

Posted: 20 Feb 2020, 00:04
by Xeo786
:?: does it support windows 7 or I am missing something :?:

seems, I do not have `IAsyncInfo` :problem:

Code: Select all

Error:  No valid COM object!

	Line#
	103: {
	104: DllCall("Combase.dll\WindowsCreateString", "wstr", string, "uint", StrLen(string), "ptr*", hString)  
	105: }
	108: {
	109: DllCall("Combase.dll\WindowsDeleteString", "ptr", hString)  
	110: }
	113: {
--->	114: AsyncInfo := ComObjQuery(Object, IAsyncInfo := "{00000036-0000-0000-C000-000000000046}")
	115: Loop
	116: {
	117: DllCall(NumGet(NumGet(AsyncInfo+0)+7*A_PtrSize), "ptr", AsyncInfo, "uint*", status)  
	118: if (status != 0)  
	119: {
	120: if (status != 1)  
	121: {

Continue running the script?

Re: Optical character recognition (OCR) with UWP API

Posted: 20 Feb 2020, 02:59
by gregster
Seems connected to UWP applications... so you are probably out of luck on WIn 7 (or 8).

Re: Optical character recognition (OCR) with UWP API

Posted: 20 Feb 2020, 12:30
by kczx3
@malcev it seems you've been posting a few of these things lately that rely pretty heavily on combase.dll. Is this an alernate way of interacting with UWP APIs than using @lexikos's ActiveScript to utilize WinRT and such?

Re: Optical character recognition (OCR) with UWP API

Posted: 20 Feb 2020, 12:42
by guest3456
rommmcek wrote: ↑
19 Feb 2020, 23:15
 Quickly tested on .bmp, .png, .gif and .jpg. Seems to be much more precise then tesseract!
tesseract was always hit and miss for me... if this is substantiallly better, then i will definitely have to look at it
malcev wrote: ↑
19 Feb 2020, 20:58
 ocr(file, language := "en")
is it possible to do it with a memory gdi/gdi+ bitmap instead of a file?

Re: Optical character recognition (OCR) with UWP API

Posted: 21 Feb 2020, 06:38
by teadrinker
It seems possible:

Code: Select all

#NoEnv
SetBatchLines, -1
Return

Esc:: ExitApp

^X::
hBitmap := HBitmapFromScreen(GetArea()*)
pIRandomAccessStream := HBitmapToRandomAccessStream(hBitmap)
DllCall("DeleteObject", "Ptr", hBitmap)
text := ocr(pIRandomAccessStream, "ru")
ObjRelease(pIRandomAccessStream)
MsgBox, % text
Return

GetArea() {
   area := []
   StartSelection(area)
   while !area.w
      Sleep, 100
   Return area
}
   
StartSelection(area) {
   handler := Func("Select").Bind(area)
   Hotkey, LButton, % handler, On
   ReplaceSystemCursors("IDC_CROSS")
}

Select(area) {
   static hGui := CreateSelectionGui()
   Hook := new WindowsHook(WH_MOUSE_LL := 14, "LowLevelMouseProc", hGui)
   Loop {
      KeyWait, LButton
      WinGetPos, X, Y, W, H, ahk_id %hGui%
   } until w > 0
   ReplaceSystemCursors("")
   Hotkey, LButton, Off
   Hook := ""
   Gui, %hGui%:Show, Hide
   for k, v in ["x", "y", "w", "h"]
      area[v] := %v%
}

ReplaceSystemCursors(IDC = "")
{
   static IMAGE_CURSOR := 2, SPI_SETCURSORS := 0x57
        , exitFunc := Func("ReplaceSystemCursors").Bind("")
        , SysCursors := { IDC_APPSTARTING: 32650
                        , IDC_ARROW      : 32512
                        , IDC_CROSS      : 32515
                        , IDC_HAND       : 32649
                        , IDC_HELP       : 32651
                        , IDC_IBEAM      : 32513
                        , IDC_NO         : 32648
                        , IDC_SIZEALL    : 32646
                        , IDC_SIZENESW   : 32643
                        , IDC_SIZENWSE   : 32642
                        , IDC_SIZEWE     : 32644
                        , IDC_SIZENS     : 32645 
                        , IDC_UPARROW    : 32516
                        , IDC_WAIT       : 32514 }
   if !IDC {
      DllCall("SystemParametersInfo", UInt, SPI_SETCURSORS, UInt, 0, UInt, 0, UInt, 0)
      OnExit(exitFunc, 0)
   }
   else  {
      hCursor := DllCall("LoadCursor", Ptr, 0, UInt, SysCursors[IDC], Ptr)
      for k, v in SysCursors  {
         hCopy := DllCall("CopyImage", Ptr, hCursor, UInt, IMAGE_CURSOR, Int, 0, Int, 0, UInt, 0, Ptr)
         DllCall("SetSystemCursor", Ptr, hCopy, UInt, v)
      }
      OnExit(exitFunc)
   }
}

CreateSelectionGui() {
   Gui, New, +hwndhGui +Alwaysontop -Caption +LastFound +ToolWindow +E0x20 -DPIScale
   WinSet, Transparent, 130
   Gui, Color, FFC800
   Return hGui
}

LowLevelMouseProc(nCode, wParam, lParam) {
   static WM_MOUSEMOVE := 0x200, WM_LBUTTONUP := 0x202
        , coords := [], startMouseX, startMouseY, hGui
        , timer := Func("LowLevelMouseProc").Bind("timer", "", "")
   
   if (nCode = "timer") {
      while coords[1] {
         point := coords.RemoveAt(1)
         mouseX := point[1], mouseY := point[2]
         x := startMouseX < mouseX ? startMouseX : mouseX
         y := startMouseY < mouseY ? startMouseY : mouseY
         w := Abs(mouseX - startMouseX)
         h := Abs(mouseY - startMouseY)
         try Gui, %hGUi%: Show, x%x% y%y% w%w% h%h% NA
      }
   }
   else {
      (!hGui && hGui := A_EventInfo)
      if (wParam = WM_LBUTTONUP)
         startMouseX := startMouseY := ""
      if (wParam = WM_MOUSEMOVE)  {
         mouseX := NumGet(lParam + 0, "Int")
         mouseY := NumGet(lParam + 4, "Int")
         if (startMouseX = "") {
            startMouseX := mouseX
            startMouseY := mouseY
         }
         coords.Push([mouseX, mouseY])
         SetTimer, % timer, -10
      }
      Return DllCall("CallNextHookEx", Ptr, 0, Int, nCode, UInt, wParam, Ptr, lParam)
   }
}

class WindowsHook {
   __New(type, callback, eventInfo := "", isGlobal := true) {
      this.callbackPtr := RegisterCallback(callback, "Fast", 3, eventInfo)
      this.hHook := DllCall("SetWindowsHookEx", "Int", type, "Ptr", this.callbackPtr
                                              , "Ptr", !isGlobal ? 0 : DllCall("GetModuleHandle", "UInt", 0, "Ptr")
                                              , "UInt", isGlobal ? 0 : DllCall("GetCurrentThreadId"), "Ptr")
   }
   __Delete() {
      DllCall("UnhookWindowsHookEx", "Ptr", this.hHook)
      DllCall("GlobalFree", "Ptr", this.callBackPtr, "Ptr")
   }
}

HBitmapFromScreen(X, Y, W, H) {
   HDC := DllCall("GetDC", "Ptr", 0, "UPtr")
   HBM := DllCall("CreateCompatibleBitmap", "Ptr", HDC, "Int", W, "Int", H, "UPtr")
   PDC := DllCall("CreateCompatibleDC", "Ptr", HDC, "UPtr")
   DllCall("SelectObject", "Ptr", PDC, "Ptr", HBM)
   DllCall("BitBlt", "Ptr", PDC, "Int", 0, "Int", 0, "Int", W, "Int", H
                   , "Ptr", HDC, "Int", X, "Int", Y, "UInt", 0x00CC0020)
   DllCall("DeleteDC", "Ptr", PDC)
   DllCall("ReleaseDC", "Ptr", 0, "Ptr", HDC)
   Return HBM
}

HBitmapToRandomAccessStream(hBitmap) {
   static IID_IRandomAccessStream := "{905A0FE1-BC53-11DF-8C49-001E4FC686DA}"
        , IID_IPicture            := "{7BF80980-BF32-101A-8BBB-00AA00300CAB}"
        , PICTYPE_BITMAP := 1
        , BSOS_DEFAULT   := 0
        
   DllCall("Ole32\CreateStreamOnHGlobal", "Ptr", 0, "UInt", true, "PtrP", pIStream, "UInt")
   
   VarSetCapacity(PICTDESC, sz := 8 + A_PtrSize*2, 0)
   NumPut(sz, PICTDESC)
   NumPut(PICTYPE_BITMAP, PICTDESC, 4)
   NumPut(hBitmap, PICTDESC, 8)
   riid := CLSIDFromString(IID_IPicture, GUID1)
   DllCall("OleAut32\OleCreatePictureIndirect", "Ptr", &PICTDESC, "Ptr", riid, "UInt", false, "PtrP", pIPicture, "UInt")
   ; IPicture::SaveAsFile
   DllCall(NumGet(NumGet(pIPicture+0) + A_PtrSize*15), "Ptr", pIPicture, "Ptr", pIStream, "UInt", true, "UIntP", size, "UInt")
   riid := CLSIDFromString(IID_IRandomAccessStream, GUID2)
   DllCall("ShCore\CreateRandomAccessStreamOverStream", "Ptr", pIStream, "UInt", BSOS_DEFAULT, "Ptr", riid, "PtrP", pIRandomAccessStream, "UInt")
   ObjRelease(pIPicture)
   ObjRelease(pIStream)
   Return pIRandomAccessStream
}

CLSIDFromString(IID, ByRef CLSID) {
   VarSetCapacity(CLSID, 16, 0)
   if res := DllCall("ole32\CLSIDFromString", "WStr", IID, "Ptr", &CLSID, "UInt")
      throw Exception("CLSIDFromString failed. Error: " . Format("{:#x}", res))
   Return &CLSID
}

ocr(IRandomAccessStream, language := "en")
{
   static OcrEngineClass, OcrEngineObject, MaxDimension, LanguageClass, LanguageObject, CurrentLanguage, StorageFileClass, BitmapDecoderClass
   if (OcrEngineClass = "")
   {
      CreateClass("Windows.Globalization.Language", ILanguageFactory := "{9B0252AC-0C27-44F8-B792-9793FB66C63E}", LanguageClass)
      CreateClass("Windows.Graphics.Imaging.BitmapDecoder", IStorageFileStatics := "{438CCB26-BCEF-4E95-BAD6-23A822E58D01}", BitmapDecoderClass)
      CreateClass("Windows.Media.Ocr.OcrEngine", IOcrEngineStatics := "{5BFFA85A-3384-3540-9940-699120D428A8}", OcrEngineClass)
      DllCall(NumGet(NumGet(OcrEngineClass+0)+6*A_PtrSize), "ptr", OcrEngineClass, "uint*", MaxDimension)   ; MaxImageDimension
   }
   if (CurrentLanguage != language)
   {
      if (LanguageObject != "")
      {
         ObjRelease(LanguageObject)
         ObjRelease(OcrEngineObject)
         LanguageObject := OcrEngineObject := ""
      }
      CreateHString(language, hString)
      DllCall(NumGet(NumGet(LanguageClass+0)+6*A_PtrSize), "ptr", LanguageClass, "ptr", hString, "ptr*", LanguageObject)   ; CreateLanguage
      DeleteHString(hString)
      DllCall(NumGet(NumGet(OcrEngineClass+0)+9*A_PtrSize), "ptr", OcrEngineClass, ptr, LanguageObject, "ptr*", OcrEngineObject)   ; TryCreateFromLanguage
      if (OcrEngineObject = 0)
      {
         msgbox Can not use language "%language%" for OCR, please install language pack.
         ExitApp
      }
      CurrentLanguage := language
   }
   DllCall(NumGet(NumGet(BitmapDecoderClass+0)+14*A_PtrSize), "ptr", BitmapDecoderClass, "ptr", IRandomAccessStream, "ptr*", BitmapDecoderObject)   ; CreateAsync
   WaitForAsync(BitmapDecoderObject, BitmapDecoderObject1)
   BitmapFrame := ComObjQuery(BitmapDecoderObject1, 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
   }
   SoftwareBitmap := ComObjQuery(BitmapDecoderObject1, IBitmapFrameWithSoftwareBitmap := "{FE287C9A-420C-4963-87AD-691436E08383}")
   DllCall(NumGet(NumGet(SoftwareBitmap+0)+6*A_PtrSize), "ptr", SoftwareBitmap, "ptr*", BitmapFrame1)   ; GetSoftwareBitmapAsync
   WaitForAsync(BitmapFrame1, BitmapFrame2)
   DllCall(NumGet(NumGet(OcrEngineObject+0)+6*A_PtrSize), "ptr", OcrEngineObject, ptr, BitmapFrame2, "ptr*", OcrResult)   ; RecognizeAsync
   WaitForAsync(OcrResult, OcrResult1)
   DllCall(NumGet(NumGet(OcrResult1+0)+6*A_PtrSize), "ptr", OcrResult1, "ptr*", lines)   ; get_Lines
   DllCall(NumGet(NumGet(lines+0)+7*A_PtrSize), "ptr", lines, "int*", count)   ; count
   loop % count
   {
      DllCall(NumGet(NumGet(lines+0)+6*A_PtrSize), "ptr", lines, "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)
      OcrLine := ""
   }
   ObjRelease(BitmapDecoderObject)
   ObjRelease(BitmapDecoderObject1)
   ObjRelease(SoftwareBitmap)
   ObjRelease(BitmapFrame)
   ObjRelease(BitmapFrame1)
   ObjRelease(BitmapFrame2)
   ObjRelease(OcrResult)
   ObjRelease(OcrResult1)
   ObjRelease(lines)
   BitmapDecoderObject := BitmapDecoderObject1 := SoftwareBitmap := BitmapFrame := BitmapFrame1 := BitmapFrame2 := OcrResult := OcrResult1 := lines := ""
   return text
}

CreateClass(string, interface, ByRef Class)
{
   CreateHString(string, hString)
   VarSetCapacity(GUID, 16)
   DllCall("ole32\CLSIDFromString", "wstr", interface, "ptr", &GUID)
   DllCall("Combase.dll\RoGetActivationFactory", "ptr", hString, "ptr", &GUID, "ptr*", Class)
   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(Object, ByRef ObjectResult)
{
   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)
         {
            msgbox AsyncInfo status error.
            ExitApp
         }
         ObjRelease(AsyncInfo)
         AsyncInfo := ""
         break
      }
      sleep 10
   }
   DllCall(NumGet(NumGet(Object+0)+8*A_PtrSize), "ptr", Object, "ptr*", ObjectResult)   ; GetResults
}

Re: Optical character recognition (OCR) with UWP API

Posted: 21 Feb 2020, 10:09
by Relayer
Of course results will vary depending on the input image but I did a side-by-side comparison on a scanned legal document with Tesseract that uses an image preprocessed with Letptonica. I fed the raw image and the preprocessed version to this script. Both Tesseract and this script make mistakes in different areas but on average the same amount of hand editing needs to be done to clean it up. Now it would be nice if I could concoct an algorithm to combine the two outputs to take advantage of what each does well.

Relayer

Re: Optical character recognition (OCR) with UWP API

Posted: 21 Feb 2020, 20:13
by malcev
kczx3 wrote: ↑
20 Feb 2020, 12:30
 @malcev it seems you've been posting a few of these things lately that rely pretty heavily on combase.dll. Is this an alernate way of interacting with UWP APIs than using @lexikos's ActiveScript to utilize WinRT and such?
I think Yes, but there are some difficulties.
For example if We want to send screenshot instead of file We can do it like teadrinker create RandomAccessStream and send it.
But if We want to do it with other method - lockbits with gdi+ and send Stride to UWP image buffer then We will have difficulties.
SoftwareBitmap can be created with 4 ways
1) from an image file with BitmapDecoder (as in code at 1 post)
2) from a WriteableBitmap
3) programmatically
4) from a Direct3D surface
https://docs.microsoft.com/en-us/windows/uwp/audio-video-camera/imaging
I tried to create SoftwareBitmap from WriteableBitmap (with adding our stride in Bufffer) but without any success - I got error 0x8001010E (RPC_E_WRONG_THREAD)

Code: Select all

CreateClass("Windows.UI.Xaml.Media.Imaging.WriteableBitmap", IWriteableBitmapFactory := "{5563EBB1-3EF2-42C5-9C6D-1CF5DCC041FF}", WriteableBitmapFactory)
msgbox % DllCall(NumGet(NumGet(WriteableBitmapFactory+0)+6*A_PtrSize), "ptr", WriteableBitmapFactory, "int", 100, "int", 100, "ptr*", WriteableBitmap)   ; WriteableBitmap

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, "uint")
   if (result != 0)
   {
      if (result = 0x80004002)
         msgbox No such interface supported
      else if (result = 0x80040154)
         msgbox Class not registered
      else
         msgbox error - %result%
   }
   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)
}
To get rid of this error We have to use dispatcher.
https://docs.microsoft.com/en-us/uwp/api/windows.ui.core.coredispatcher
But I can not get this coredispatcher class from CoreApplication Class because CoreApplication Class API is supported in native apps only.
https://docs.microsoft.com/en-us/uwp/api/windows.applicationmodel.core.coreapplication
Then I tried to get dispatcher from window class
https://docs.microsoft.com/en-us/uwp/api/windows.ui.xaml.window
But I can not do it because I get 0 for current window

Code: Select all

CreateClass("Windows.UI.Xaml.Window", IWindowStatics := "{93328409-4EA1-4AFA-83DC-0C4E73E88BB1}", WindowClass)
DllCall(NumGet(NumGet(WindowClass+0)+6*A_PtrSize), "ptr", WindowClass, "ptr*", Current)   ; Current
msgbox % Current

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, "uint")
   if (result != 0)
   {
      if (result = 0x80004002)
         msgbox No such interface supported
      else if (result = 0x80040154)
         msgbox Class not registered
      else
         msgbox error - %result%
   }
   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)
}
PS I replace ObjRelease(StorageFileObject0) to ObjRelease(StorageFileObject) in 1 post. :oops:

Re: Optical character recognition (OCR) with UWP API

Posted: 23 Feb 2020, 12:56
by blue83
Hi,

How to use other language than "en"? or use them both en+de or en+it or ...?

Also how to use OCR only on part of the page?

Thank you

Re: Optical character recognition (OCR) with UWP API

Posted: 23 Feb 2020, 17:21
by neogna2
teadrinker wrote: ↑
21 Feb 2020, 06:38
 It seems possible
Super useful script! Here is a tiny enhancement to the hotkeys in your script.

Replace this line

Code: Select all

KeyWait, LButton
With this

Code: Select all

KeyWait, LButton
WinGetPos, , , WW, , ahk_id %hGui%
if !WW
	KeyWait, LButton, D
That lets us also do (click, release, draw area, click again) which can be less of a strain when using a touchpad compared to the regular (click, hold, draw area while still holding, release) workflow.

Re: Optical character recognition (OCR) with UWP API

Posted: 23 Feb 2020, 17:23
by malcev
How to use other language than "en"? or use them both en+de or en+it or ...?
I update 1 post.
how to use OCR only on part of the page?
It depends on how do You want to put coordinates.
1) If You want to send it directly to function then I can add such feature.
2) If You want to choose coordinates with mouse, then take a look at post of teadrinker

Re: Optical character recognition (OCR) with UWP API

Posted: 24 Feb 2020, 07:15
by teadrinker
neogna2
I've made corrections.

Re: Optical character recognition (OCR) with UWP API

Posted: 24 Feb 2020, 10:12
by blue83
malcev wrote: ↑
23 Feb 2020, 17:23
How to use other language than "en"? or use them both en+de or en+it or ...?
I update 1 post.
how to use OCR only on part of the page?
It depends on how do You want to put coordinates.
1) If You want to send it directly to function then I can add such feature.
2) If You want to choose coordinates with mouse, then take a look at post of teadrinker
Hi @malcev Thank you for the languages.

And yes, I want to add coordinates inside code, not to drag with a mouse.

Thank you

Re: Optical character recognition (OCR) with UWP API

Posted: 24 Feb 2020, 10:49
by guest3456
blue83 wrote: ↑
24 Feb 2020, 10:12
And yes, I want to add coordinates inside code, not to drag with a mouse.
teadrinker's code lets you specify the coordinates inside the code.. just change the first line:

Code: Select all

hBitmap := HBitmapFromScreen(GetArea()*)
;to
hBitmap := HBitmapFromScreen(X, Y, W, H)

Re: Optical character recognition (OCR) with UWP API

Posted: 24 Feb 2020, 11:12
by blue83
guest3456 wrote: ↑
24 Feb 2020, 10:49
blue83 wrote: ↑
24 Feb 2020, 10:12
And yes, I want to add coordinates inside code, not to drag with a mouse.
teadrinker's code lets you specify the coordinates inside the code.. just change the first line:

Code: Select all

hBitmap := HBitmapFromScreen(GetArea()*)
;to
hBitmap := HBitmapFromScreen(X, Y, W, H)

Thank you on your help :)

Re: Optical character recognition (OCR) with UWP API

Posted: 24 Feb 2020, 12:03
by malcev
Ok. I thought that You want to crop image file, but not screenshot.

Re: Optical character recognition (OCR) with UWP API

Posted: 24 Feb 2020, 14:27
by blue83
no problem.. @malcev this is great OCR tool for use with Ahk..

Re: Optical character recognition (OCR) with UWP API

Posted: 24 Feb 2020, 16:02
by r2997790
@malcev, thank you so much for this alternative OCR method. I'm excited to try this... excuse my ignorance, could you please tell me any dependencies I need to have to run this?

I'm getting a no valid COM object error: https://i.imgur.com/gobIvII.jpg ... running windows 10.

Is there a way I can trouble shoot this?

Many thanks
R

Re: Optical character recognition (OCR) with UWP API

Posted: 24 Feb 2020, 16:13
by malcev
Hmm. I think it should not have dependencies.
I was to lazy to check ErrorLevels.
If You write this it works?

Code: Select all

msgbox % ocr("ShowAvailableLanguages")
May be file does not exist?
All times are UTC-05:00
Page 1 of 9
Powered by phpBB® Forum Software © phpBB Limited
https://www.phpbb.com/