[tesseract-ocr] Very low accurate with tesseract

now I am trying to recognize license plate number with tesseract in my python project. I already install tesseract and recognize by using them. but the accurate is very low. I wish anyone help me to solve this problem. Thanks -- You received this message because you are subscribed to the Google

Re: [tesseract-ocr] how to see which fonts are used in .traineddata files

Hi Zdenko, Per you suggestion I have installed the latest version of tesseract (Ver 5), and I played with the psm. I get the best result using --psm 11, like you did. Other values of psm give poor results. npsm 11 is the best, but it is still not good. How do I create custom image segmentation