We morph close to fix and broken lines and smooth the table. Repair horizontal/vertical lines and extract each ROI. This will effectively make the text into tiny noise so we find contours and filter using contour area to remove them. We create a rectangular kernel and perform opening to only keep the horizontal/vertical lines. Load image, convert to grayscale, and Otsu's threshold. Here's a continuation of your approach with slight modifications. #Now we have badly detected boxes image as shown If(th3.shape=.7*medianheight and w/h > 0.9): # initialize kernels for table boundaries detections I don't know which part I'm doing wrong but if there's anything I should try or maybe change/add in my question please please tell me. I cannot get clearly separated boxes using real lines, I've tried this on an image that was edited in paint(as shown below) to add digits and it works. I cannot detect text only to perform OCR and proper bounding boxes aren't being generated like below: I am trying to extract each box separately and perform OCR but when I try to detect horizontal and vertical lines and then detect boxes it's returning the following image:Īnd when I try to perform other transformations to detect text (erode and dilate) some remains of lines are still coming along with text like below: I have scanned images which have tables as shown in this image:
0 kommentar(er)
