[tesseract-ocr] Help with detecting a code on an image

Hello, I want to detect a code (combination of characters) on an image in python. I already tried EasyOCR and Tesseract Open Source OCR Engine but noone could detect the characters. I also tried to preprocess th

[tesseract-ocr] Re: Arabic Club ID Card OCR

Were you able to fix this issue? On Friday, November 26, 2021 at 3:09:36 PM UTC+3 eng.ahmed@gmail.com wrote: > I have a use case where I want to make text recognition for Arabic Club ID > > I have attached the before and after processing images > > Using the below command > *tesseract out

Re: [tesseract-ocr] Combining traineddata files

As far as I know, there is no tool that can merge finished training. IMO for LSMT it should work as incremental training e.g. you used the output of fine-tuning as input for the next fine-tuning... (I never tried it ;-) ) Zdenko so 22. 10. 2022 o 9:36 Umanda Dikwatta napísal(a): > > LSTM > On

Re: [tesseract-ocr] Help with detecting a code on an image

Did you try all the preprocessing steps? Rotation / Deskewing ? I think Tesseract finds it difficult to identify skewed images. On Mon, Oct 31, 2022 at 1:17 PM nabil-ak wrote: > Hello, > > I want to detect a code (combination of characters) on an image in python. > > I already tried EasyOCR

Re: [tesseract-ocr] Hello,

Hello, how did you come to the conclusion you need to do training? You did not post any examples, but for simple solutions, there are plenty of examples on the internet (search for ALPR): https://pyimagesearch.com/2020/09/21/opencv-automatic-license-number-plate-recognition-anpr-with-python/ http

Re: [tesseract-ocr] Hello,

[image: 2.jpg] ในวันที่ จ. 31 ต.ค. 2022 เวลา 16:49 Zdenko Podobny เขียนว่า: > Hello, > > how did you come to the conclusion you need to do training? > > You did not post any examples, but for simple solutions, there are plenty > of examples on the internet (search for ALPR): > > https://pyimages

Re: [tesseract-ocr] Hello,

here it is example of license plate that i want to use tesseract to recgonize, i have been train using my own language for many time but it didn't work best ในวันที่ จ. 31 ต.ค. 2022 เวลา 18:26 ທ. ວັນລະຄານ ອິນສີຊຽງໃຫມ່ 2cpr2 < chanthakhaninsyxieng...@gmail.com> เขียนว่า: > [image: 2.jpg] > > ในวัน

Re: [tesseract-ocr] Help with detecting a code on an image

*I also tried Rotation but its still not working.* *These are the preprocessing steps that i used:* import cv2 import pytesseract import numpy as np from scipy import ndimage img = cv2.imread('voucher.png') img = cv2.bitwise_not(img) img = cv2.resize(img, None, fx=1.2, fy=1.2, interpolation=cv

Re: [tesseract-ocr] Help with detecting a code on an image

https://imagetotext.info/ If i use a website like this one it can extract the text perfectly and they also use tesseract. There has to be some preproccesing/setting that makes tesseract detect the text perfectly. nabil-ak schrieb am Montag, 31. Oktober 2022 um 13:55:56 UTC+1: > *I also tried R

Re: [tesseract-ocr] Help with detecting a code on an image

So I think you could also try using some morphological transformation; I feel like dilation could help a lot too On Monday, October 31, 2022 at 2:01:36 PM UTC-4 nabil-ak wrote: > https://imagetotext.info/ > > If i use a website like this one it can extract the text perfectly and > they also us

Re: [tesseract-ocr] Help with detecting a code on an image

Hi, Combination of image deskewing and image inversion should work. Use PSM 11 on processed image, it will detect most of the characters. Thanks, Nikhil On Tue, Nov 1, 2022, 6:16 AM kwmz...@gmail.com wrote: > So I think you could also try using some morphological transformation; I > feel like