Inside attachment under "GDPictureOCRIssueWithCustomTraineddataFile\GDPictureOCRIssueWithCustomTraineddataFileTestData\TestData\CustomDictionary" folder you can find custom.traineddata file, but when I am using this custom.traineddata file with OCRTesseractDoOCR() I am getting blank result with the error "actual_tessdata_num_entries_ <= TESSDATA_NUM_ENTRIES:Error:Assert failed:in file ..\ccuti
l\tessdatamanager.cpp, line 48" .
Inside attachment I have provided datafiles which I used to create the custom.traineddata file under "GDPictureOCRIssueWithCustomTraineddataFile\GDPictureOCRIssueWithCustomTraineddataFileTestData\TestData\DataUsedForCreatingCustomDictionary\" folder . I have also provided sample application inside the attachment for this problem. We are using GDPicture.NET 9.
I also found that if I use this created custom.traineddata file with Google Tesseract-ocr (tesseract.exe) it is gives proper result for the input.
What could be problem with OCRTesseractDoOCR()? Am I missing any data file for creating the .traineddata file?
- (1.54 MiB) Downloaded 106 times
The reason for the error could be a different trained data file format, different Tesseract engine version, etc. As suggested in the other post, could you please give us more details about the ocr challenges you want to solve?
May I ask you to share the input data for the training process and your training procedure? This way I would be able to try and reproduce your issue using the latest versions of GdPicture and Tesseract tools.
Who is online
Users browsing this forum: No registered users and 1 guest