Well it doesn't seems to be a problem with fonts Training. I tried capturing the same image without skewness and it perfectly worked out. Not sure why tesseract doesn't works with bit skewed texts in images..
On Sat, Oct 27, 2018 at 5:22 PM Vinod Gattani <[email protected]> wrote: > It gave "|" as text. > > When resized to 50*50, text is "N\". You should check whether font used in > the image, is a part of fonts on which English language was trained. > > Thanks > > On Sat, Oct 27, 2018 at 3:46 PM <[email protected]> wrote: > >> Can you try this new attached image for Alphabet "M" ? >> >> On Saturday, October 27, 2018 at 12:22:45 PM UTC+5:30, >> [email protected] wrote: >>> >>> I am using Pytesseract to recognise an image for number 5 and I'm >>> stunned that even after applying various filters like GlaussianBlur and >>> Threshold and applying dilation and erosion to remove the noise it still >>> not able to identify the image. >>> >>> >>> I am using Eng Trained data by default. Not sure where I am going wrong. >>> Do I need to include any other training file here? >>> >>> >>> Filters Tried: >>> >>> >>> 1: cv2.threshold(cv2.GaussianBlur(img, (9, 9), 0), 0, 255, >>> cv2.THRESH_BINARY + cv2.THRESH_OTSU)[1], >>> >>> 2: cv2.threshold(cv2.GaussianBlur(img, (7, 7), 0), 0, 255, >>> cv2.THRESH_BINARY + cv2.THRESH_OTSU)[1], >>> >>> 3: cv2.threshold(cv2.GaussianBlur(img, (5, 5), 0), 0, 255, >>> cv2.THRESH_BINARY + cv2.THRESH_OTSU)[1], >>> >>> 4: cv2.threshold(cv2.medianBlur(img, 5), 0, 255, >>> cv2.THRESH_BINARY + cv2.THRESH_OTSU)[1], >>> >>> 5: cv2.threshold(cv2.medianBlur(img, 3), 0, 255, >>> cv2.THRESH_BINARY + cv2.THRESH_OTSU)[1], >>> >>> 6: cv2.adaptiveThreshold(cv2.GaussianBlur(img, (5, 5), 0), >>> 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY, 31, 2), >>> >>> 7: cv2.adaptiveThreshold(cv2.medianBlur(img, 3), 255, >>> cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY, 31, 2), >>> >>> >>> >>> *Training Data:* >>> >>> eng.traineddata >>> >>> >>> *Original Image: See Attached* >>> >>> >>> >>> >>> >>> -- >> You received this message because you are subscribed to the Google Groups >> "tesseract-ocr" group. >> To unsubscribe from this group and stop receiving emails from it, send an >> email to [email protected]. >> To post to this group, send email to [email protected]. >> Visit this group at https://groups.google.com/group/tesseract-ocr. >> To view this discussion on the web visit >> https://groups.google.com/d/msgid/tesseract-ocr/a5efe646-bc59-4492-802a-7b69320d4430%40googlegroups.com >> <https://groups.google.com/d/msgid/tesseract-ocr/a5efe646-bc59-4492-802a-7b69320d4430%40googlegroups.com?utm_medium=email&utm_source=footer> >> . >> For more options, visit https://groups.google.com/d/optout. >> > -- > You received this message because you are subscribed to the Google Groups > "tesseract-ocr" group. > To unsubscribe from this group and stop receiving emails from it, send an > email to [email protected]. > To post to this group, send email to [email protected]. > Visit this group at https://groups.google.com/group/tesseract-ocr. > To view this discussion on the web visit > https://groups.google.com/d/msgid/tesseract-ocr/CAN557az79nE5VXF0uxq%2BsUv-p%2BfhOM1bx%3DKK9YG1zLUau2hdow%40mail.gmail.com > <https://groups.google.com/d/msgid/tesseract-ocr/CAN557az79nE5VXF0uxq%2BsUv-p%2BfhOM1bx%3DKK9YG1zLUau2hdow%40mail.gmail.com?utm_medium=email&utm_source=footer> > . > For more options, visit https://groups.google.com/d/optout. > -- You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. To post to this group, send email to [email protected]. Visit this group at https://groups.google.com/group/tesseract-ocr. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/CANffUEY%2BnidmfnanRbQEEhCO%3DrtVLkfy%2BGESLbkksc6m45uX%3DQ%40mail.gmail.com. For more options, visit https://groups.google.com/d/optout.
