[tesseract-ocr] Unable to read the TIFF image properly

2020-04-27 Thread Santanu Roy
Hi, Please find attached TIFF image file. The tesseract OCR is reading the 0 (Zeros) as alphabet 'O'. I'm using a libtesseract302.dll for this. Please help me in this regards Thanks -- You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To

[tesseract-ocr] Engineering drawings OCR

2020-04-27 Thread pranaya mhatre
Hi, I am using tesseract v4.1.0-bibtag19 in windows 10. I am extracting text from engineering drawings made in auto cad and the images are clear. but i am unable to extract all text from drawings and also getting some garbage text. Is it required to train tesseract for engineering drawings

Re: [tesseract-ocr] Training data generation using text lines

2020-04-27 Thread Suresh Anand
OpenCV is the answer On Tue, 28 Apr 2020, 08:03 Purushotham Rao Eravalli, wrote: > I am facing issue with text image creation, I am unable to generate the > noise or disturbances in the image, please can someone help me how to > generate image files from text with different type of noise in the

[tesseract-ocr] Training data generation using text lines

2020-04-27 Thread Purushotham Rao Eravalli
I am facing issue with text image creation, I am unable to generate the noise or disturbances in the image, please can someone help me how to generate image files from text with different type of noise in the image -- You received this message because you are subscribed to the Google Groups

Re: [tesseract-ocr] Re: traineddata for consolas font

2020-04-27 Thread Marco Peretti
Hello Martin, I am afraid I won't be of much help as it was a one-off experiment, long forgotten. I was investigating exfiltrating information via the Remote Desktop Protocol (RDP) and I haven't used Tesseract since then. My feeling at the time was that Tesseract was better suited for regular