Yeah my python is rusty but I do have experience with it. What do you
suggest I begin with?
On Monday 15 July 2024 at 20:29:38 UTC+8 renec...@gmail.com wrote:
> If you have a python knowledge I can help.
>
> Le lun. 15 juil. 2024 à 05:39, vizier87 <abdulh...@gmail.com> a écrit :
>
>> Anyone?
>>
>> Thanks!
>>
>> On Sunday 14 July 2024 at 14:13:38 UTC+8 vizier87 wrote:
>>
>>> Hi everyone, I need some help with the flow of the Tesseract
>>> pre-procesing.
>>>
>>> Here's a thermography image I'm attempting to detect:
>>> [image: 6.png]
>>>
>>>
>>> the code I'm using in .NET is the following:
>>> Try
>>>
>>> ' Load the image using OpenCvSharp
>>> Dim src As Mat = Cv2.ImRead(imagePath, ImreadModes.Grayscale)
>>>
>>>
>>> ' Apply preprocessing steps
>>> Dim processedImage As New Mat()
>>> Cv2.Resize(src, processedImage, New Size(src.Width * size,
>>> src.Height * size)) ' Resize to double the size
>>>
>>> Cv2.Threshold(processedImage, processedImage, threshold, maxval,
>>> ThresholdTypes.Otsu) ' Apply thresholding
>>>
>>> ' Save the preprocessed image to a temporary file on the desktop
>>> Dim desktopPath As String =
>>> Environment.GetFolderPath(Environment.SpecialFolder.Desktop)
>>> Dim tempImagePath As String =
>>> System.IO.Path.Combine(desktopPath, "temp_image.png")
>>> Cv2.ImWrite(tempImagePath, processedImage)
>>>
>>>
>>>
>>> Using engine As New TesseractEngine("C:\Program
>>> Files\Tesseract-OCR\tessdata", "eng", EngineMode.Default)
>>> ' Load the preprocessed image
>>> Using img As Pix = Pix.LoadFromFile(tempImagePath)
>>> ' Perform OCR
>>> Using page As Page = engine.Process(img)
>>> ' Get the recognized text
>>> Dim recognizedText As String = page.GetText()
>>> Return recognizedText
>>> End Using
>>> End Using
>>> End Using
>>>
>>>
>>>
>>>
>>>
>>>
>>> Catch ex As Exception
>>> Return "Error performing OCR: " & ex.Message
>>> End Try
>>> End Function
>>>
>>>
>>> admittedly, this was done with the help of a particular AI, but I've
>>> been tuning it in all the places (size, threshold and maxval) and still got
>>> nothing.
>>>
>>> Quite sure the flow is incorrect. Can anyone suggest any additional
>>> pre-processing?
>>>
>>> Thanks.
>>>
>>>
>>> --
>> You received this message because you are subscribed to the Google Groups
>> "tesseract-ocr" group.
>> To unsubscribe from this group and stop receiving emails from it, send an
>> email to tesseract-oc...@googlegroups.com.
>> To view this discussion on the web visit
>> https://groups.google.com/d/msgid/tesseract-ocr/98b7b7c2-a80d-4b66-98d9-d8bea769856bn%40googlegroups.com
>>
>> <https://groups.google.com/d/msgid/tesseract-ocr/98b7b7c2-a80d-4b66-98d9-d8bea769856bn%40googlegroups.com?utm_medium=email&utm_source=footer>
>> .
>>
>
--
You received this message because you are subscribed to the Google Groups
"tesseract-ocr" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to tesseract-ocr+unsubscr...@googlegroups.com.
To view this discussion on the web visit
https://groups.google.com/d/msgid/tesseract-ocr/1a2bdf39-1173-4c6d-bf84-d7adc982be07n%40googlegroups.com.
