How to detect the text above lines using OpenCV in Python

Question

I am interested in detecting lines (which I managed to figure out using hough transform) and the text above it.

My test image is below:

The code I have written is below. ( I have edited so that I can loop through the coordinates of each line)

import cv2
import numpy as np

img=cv2.imread('test3.jpg')
#img=cv2.resize(img,(500,500))
imgGray=cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
imgEdges=cv2.Canny(imgGray,100,250)
imgLines= cv2.HoughLinesP(imgEdges,1,np.pi/180,230, minLineLength = 700, maxLineGap = 100)
imgLinesList= list(imgLines)

a,b,c=imgLines.shape
line_coords_list = []
for i in range(a):
    line_coords_list.append([(int(imgLines[i][0][0]), int(imgLines[i][0][1])), (int(imgLines[i][0][2]), int(imgLines[i][0][3]))])

print(line_coords_list)#[[(85, 523), (964, 523)], [(85, 115), (964, 115)], [(85, 360), (964, 360)], [(85, 441), (964, 441)], [(85, 278), (964, 278)], [(85, 197), (964, 197)]]

roi= img[int(line_coords_list[0][0][1]): int(line_coords_list[0][1][1]), int(line_coords_list[0][0][0]) : int(line_coords_list[0][1][0])]
print(roi) # why does this print an empty list?
cv2.imshow('Roi NEW',roi) 

Now I just don't know how to detect the region of interest above those lines. Is it possible to say crop out each line and have images say roi_1 , roi_2 , roi_n where each roi is the text above the first line, the text above the second line etc?

I would like the output to be something like this.

Answer 1

Here is one way to do that in Python/OpenCV.

• Read the input
• Convert to gray
• Threshold (OTSU) so that text is white on black background
• Apply morphology dilate with horizontal kernel to blur text in a line together
• Apply morphology open with a vertical kernel to remove the thin lines from the dotted lines
• Get the contours
• Find the contour that has the lowest Y bounding box value (top-most box)
• Draw all the bounding boxes on the input except for the topmost one
• Save results

Input:

import cv2
import numpy as np

# load image
img = cv2.imread("text_above_lines.jpg")

# convert to gray
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

# threshold the grayscale image
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]

# use morphology erode to blur horizontally
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (151, 3))
morph = cv2.morphologyEx(thresh, cv2.MORPH_DILATE, kernel)

# use morphology open to remove thin lines from dotted lines
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (3, 17))
morph = cv2.morphologyEx(morph, cv2.MORPH_OPEN, kernel)

# find contours
cntrs = cv2.findContours(morph, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cntrs = cntrs[0] if len(cntrs) == 2 else cntrs[1]

# find the topmost box
ythresh = 1000000
for c in cntrs:
    box = cv2.boundingRect(c)
    x,y,w,h = box
    if y < ythresh:
        topbox = box
        ythresh = y

# Draw contours excluding the topmost box
result = img.copy()
for c in cntrs:
    box = cv2.boundingRect(c)
    if box != topbox:
        x,y,w,h = box
        cv2.rectangle(result, (x, y), (x+w, y+h), (0, 0, 255), 2)

# write result to disk
cv2.imwrite("text_above_lines_threshold.png", thresh)
cv2.imwrite("text_above_lines_morph.png", morph)
cv2.imwrite("text_above_lines_lines.jpg", result)

#cv2.imshow("GRAY", gray)
cv2.imshow("THRESH", thresh)
cv2.imshow("MORPH", morph)
cv2.imshow("RESULT", result)
cv2.waitKey(0)
cv2.destroyAllWindows()

Thresholded image:

Morphology image:

Result: