I have the 6 page tif document which takes approximately 120 seconds to be converted into searchable PDF.
This document has, in addition to the text, images, stamps and handwritten words.
Is there a param paramenter that can be added to the code to optimize the process?
In pure text the tessaract has a very good performance.


I am using the following code for conversion:

Sub OCR()
OcrApi.LicenseKey = "XXXXX-XXXX"
Try
Dim startTime As DateTime = DateTime.Now
Dim ocr = OcrApi.Create
ocr.Init(Languages.Portuguese, My.Application.Info.DirectoryPath & "\", OcrEngineMode.OEM_TESSERACT_ONLY)
Dim OutPdf = OcrPdfRenderer.Create("C:\OCR\" & Format(DateTime.Now, "yyyy-MM-dd-HHmmssfff"), My.Application.Info.DirectoryPath & "\tessdata\")
OutPdf.BeginDocument("Title")
Try
ocr.ProcessPages("c:\OCR\InputFile.tif", vbFalse, 0, OutPdf)
Catch ex As Exception
MsgBox(ex.Message)
End Try
OutPdf.EndDocument()
OutPdf.Dispose()
ocr.Dispose()
MsgBox("Concluido!" & Chr(13) & "Processado em " & DateDiff(DateInterval.Second, startTime, DateTime.Now) & " segundos")
Catch ex As Exception
MsgBox(ex.Message)
End Try
End Sub

Thank you for now