I am trying to make a Japanese
OCR
app. I am getting this error while i try to initialize Tesseract
. Below are my code:
if let tesseract = G8Tesseract(language: "eng+jpn") {
tesseract.engineMode = .tesseractCubeCombined
tesseract.pageSegmentationMode = .auto
tesseract.image = image.g8_blackAndWhite()
tesseract.recognize()
textView.text = tesseract.recognizedText
}
Finally i figured out that i don't have cube files and i couldn't find searching them on github and other's site . Can anyone give me any link where i can find cube files for other language ???
Cube files are not available for all language. As i used
tesseract.engineMode = .tesseractCubeCombined
the above code, it will try to use both cube file and regular .traineddata
file . To solve this problem , i had to replace the above code as below and add only the langdata
as .traineddata
format for the specific language under a folder named tessdata
tesseract.engineMode = .tesseractOnly