Hi,
for university purpose I'm trying to do the physical segmentation of a document.
At this moment I find the connected component, both in term of characters that in term of text lines and images. This is the code and the result:
from PIL import Image
import cv2
import numpy as np
from cv2 import boundingRect, countNonZero, cvtColor, drawContours, findContours, getStructuringElement, imread, morphologyEx, pyrDown, rectangle, threshold
large = imread('./samples/icdar.jpg')
# downsample and use it for processing
rgb = pyrDown(large)
# apply grayscale
small = cvtColor(rgb, cv2.COLOR_BGR2GRAY)
# morphological gradient
morph_kernel = getStructuringElement(cv2.MORPH_ELLIPSE, (3, 3))
grad = morphologyEx(small, cv2.MORPH_GRADIENT, morph_kernel)
# binarize
_, bw = threshold(src=grad, thresh=0, maxval=255, type=cv2.THRESH_BINARY+cv2.THRESH_OTSU)
morph_kernel = getStructuringElement(cv2.MORPH_RECT, (9, 1))
# connect horizontally oriented regions
connected = morphologyEx(bw, cv2.MORPH_CLOSE, morph_kernel)
mask = np.zeros(bw.shape, np.uint8)
# find contours
im2, contours, hierarchy = findContours(connected, cv2.RETR_CCOMP, cv2.CHAIN_APPROX_SIMPLE)
# filter contours
for idx in range(0, len(hierarchy[0])):
rect = x, y, rect_width, rect_height = boundingRect(contours[idx])
# fill the contour
mask = drawContours(mask, contours, idx, (255, 255, 2555), cv2.FILLED)
# ratio of non-zero pixels in the filled region
r = float(countNonZero(mask)) / (rect_width * rect_height)
if r > 0.45 and rect_height > 8 and rect_width > 8:
rgb = rectangle(rgb, (x, y+rect_height), (x+rect_width, y), (0,255,0),1)
Image.fromarray(rgb).show()
From now I'll would merge the bounding box of the related connected component, for example those texts on the same column. Anyone know how I can do?
Thank you
