1

Using the next code I can take an image and separate it in various smaller images containing area's of interest.

import cv2
import sys

sys.path.insert(0, 'C:\\Users\\Bob\\Desktop\\Project')
sys.path.insert(0, 'C:\\Users\\Bob\\Desktop\\Project\\FOLDER')
sys.path.insert(0, 'C:\\Users\\Bob\\Desktop\\Project\\READER')

import FOLDER.folders
import READER.extractor

timestr = FOLDER.folders.timestr

################## AREA 1 ##################

# Load the image
img = cv2.imread('C:\\Users\\Bob\\Desktop\\Destination\\' + str(timestr) + '\\EXTRACTED\\' + 'area1.png')

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

# smooth the image to avoid noises
gray = cv2.medianBlur(gray,5)

# Apply adaptive threshold
thresh = cv2.adaptiveThreshold(gray,255,1,1,11,2)
thresh_color = cv2.cvtColor(thresh,cv2.COLOR_GRAY2BGR)

# apply some dilation and erosion to join the gaps - change iterations value to detect more or less area's
thresh = cv2.dilate(thresh,None,iterations = 15)
thresh = cv2.erode(thresh,None,iterations = 15)

# Find the contours
image,contours,hierarchy = cv2.findContours(thresh,cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE)

# For each contour, find the bounding rectangle and draw it
idx =0

for cnt in contours:
    idx += 1
    x,y,w,h = cv2.boundingRect(cnt)
    roi = gray[y:y + h, x:x + w]
    cv2.rectangle(img,(x,y),(x+w,y+h),(0,255,0),2)
    cv2.rectangle(thresh_color,(x,y),(x+w,y+h),(0,255,0),2)
    cv2.imwrite('C:\\Users\\Bob\\Desktop\\Destination\\' + str(timestr) + '\\EXTRACTED\\ex_area1' + str(idx) + '.png',roi)

This is an example:

Image loaded

origin

Output

output1

output2

The code give out also some minor images (let's say artifacts) which I don't want. All these images are below some certain dimensions.

selection

My question is: what I have to add to the code above to delete these images ? To delete images which is under, for example, the next dimensions: 250(width) X 60(height) pixels ?

Thank you

Tip: Used this code to detect the areas: Improve text area detection (OpenCV, Python)

lucians
  • 2,239
  • 5
  • 36
  • 64

1 Answers1

2

Just dont write them in the first place. Write only images above 60*250.

   for cnt in contours:
        idx += 1
        x,y,w,h = cv2.boundingRect(cnt)
        roi = gray[y:y + h, x:x + w]
        cv2.rectangle(img,(x,y),(x+w,y+h),(0,255,0),2)
        cv2.rectangle(thresh_color,(x,y),(x+w,y+h),(0,255,0),2)
        if (w*h>250*60):    #change this for proper settings
           cv2.imwrite('C:\\Users\\Bob\\Desktop\\Destination\\' + str(timestr) 
            + '\\EXTRACTED\\ex_area1' + str(idx) + '.png',roi)
I.Newton
  • 1,753
  • 1
  • 10
  • 14