OCRTesseract can not recognize Chinese

[Sunzhuokai]

Summary of your issue

OCRTesseract can not recognize Chinese

Environment

What did you do when you faced the problem?

//write here

Example code:

using (var ocr = OCRTesseract.Create(“tessdata", "chi_sim"))
                        {
                            ocr.Run(topRoi, out text, out _componentRects, out  _componentTexts, out  _confidences);
                        }

Output:

Just 0-9,a-Z

What did you intend to be?

[shimat]

Does your tessdata contain chi_sim.traineddata ?

[Sunzhuokai]

Does your tessdata contain chi_sim.traineddata ?

yes

[Sunzhuokai]

@shimat when i use https://github.com/charlesw/tesseract wrapper , it is works

[shimat]

I could reproduce this problem. It may be an OpenCV bug.
opencv/opencv_contrib#2062

[stale]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.

[Jerry-Gump]

I have the same problem,anything can fix it?

OK, maybe this is the reason: tesseract-ocr/tesseract#1250

[n0099]

From https://docs.opencv.org/4.7.0/d7/ddc/classcv_1_1text_1_1OCRTesseract.html#a391b1e753f0b779b72204ec15200a99a:

char_whitelist specifies the list of characters used for recognition. NULL defaults to "0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ".

opencvsharp/src/OpenCvSharp/Modules/text/OCRTesseract.cs

Line 37 in 0498156

/// null defaults to "0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ".</param>

opencvsharp/src/OpenCvSharpExtern/text.h

Line 87 in 0498156

const auto result = cv::text::OCRTesseract::create(datapath, language, char_whitelist, oem, psmode);

so manually set the whitelist to empty string "" works for me.