issue of reading -1 as 4 on images

[Hussin22]

hello Tesseract ,

i do ocr reading with java using tesseract library , but only an issue with hyphen always '-1' readed as '4' , below the readed example image : https://i.ibb.co/vxDrv2y/PN.png

this readed as : 23267764.

[Hussin22]

i m using java with tess4J 3.4.8 and eng.traineddata download from github

i need to read only numbers from 0-9 , and also '-' , 'L'

[zdenop]

Please respect guidance for posting issues - we do not provide support for 3rd party tools. Replicate problem with tesseract executable and provide necessary information (tesseract version, which trainneddata you used...)

[Hussin22]

i use this below version : <groupId>net.sourceforge.tess4j</groupId> <artifactId>tess4j</artifactId> 5.5.0

and for trained data i use : eng.traineddata

[zdenop]

One again - we do not support tess4j (3rd party solution) - replicate problem with recent tesseract executable.