Remove background text and noise from an image using image processing with OpenCV

Question

I have these images

For which I want to remove the text in the background. Only the captcha characters should remain(i.e K6PwKA, YabVzu).

Answer 1

Here are two potential approaches and a method to correct distorted text:

Method #1: Morphological operations + contour filtering

1. Obtain binary image. Load image, grayscale, then Otsu's threshold.

2. Remove text contours. Create a rectangular kernel with cv2.getStructuringElement and then perform morphological operations to remove noise.

3. Filter and remove small noise. Find contours and filter using contour area to remove small particles. We effectively remove the noise by filling in the contour with cv2.drawContours

4. Perform OCR. We invert the image then apply a slight Gaussian blur. We then OCR using Pytesseract with the --psm 6 configuration option to treat the image as a single block of text. Look at Tesseract improve quality for other methods to improve detection and Pytesseract configuration options for additional settings.

---

Input image -> Binary -> Morph opening

Contour area filtering -> Invert -> Apply blur to get result

Result from OCR

YabVzu

Code

import cv2
import pytesseract
import numpy as np

pytesseract.pytesseract.tesseract_cmd = r"C:\Program Files\Tesseract-OCR\tesseract.exe"

# Load image, grayscale, Otsu's threshold
image = cv2.imread('2.png')
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]

# Morph open to remove noise
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (2,2))
opening = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, kernel, iterations=1)

# Find contours and remove small noise
cnts = cv2.findContours(opening, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
for c in cnts:
    area = cv2.contourArea(c)
    if area < 50:
        cv2.drawContours(opening, [c], -1, 0, -1)

# Invert and apply slight Gaussian blur
result = 255 - opening
result = cv2.GaussianBlur(result, (3,3), 0)

# Perform OCR
data = pytesseract.image_to_string(result, lang='eng', config='--psm 6')
print(data)

cv2.imshow('thresh', thresh)
cv2.imshow('opening', opening)
cv2.imshow('result', result)
cv2.waitKey()     

Method #2: Color segmentation

With the observation that the desired text to extract has a distinguishable contrast from the noise in the image, we can use color thresholding to isolate the text. The idea is to convert to HSV format then color threshold to obtain a mask using a lower/upper color range. From were we use the same process to OCR with Pytesseract.

---

Input image -> Mask -> Result

Code

import cv2
import pytesseract
import numpy as np

pytesseract.pytesseract.tesseract_cmd = r"C:\Program Files\Tesseract-OCR\tesseract.exe"

# Load image, convert to HSV, color threshold to get mask
image = cv2.imread('2.png')
hsv = cv2.cvtColor(image, cv2.COLOR_BGR2HSV)
lower = np.array([0, 0, 0])
upper = np.array([100, 175, 110])
mask = cv2.inRange(hsv, lower, upper)

# Invert image and OCR
invert = 255 - mask
data = pytesseract.image_to_string(invert, lang='eng', config='--psm 6')
print(data)

cv2.imshow('mask', mask)
cv2.imshow('invert', invert)
cv2.waitKey()

Correcting distorted text

OCR works best when the image is horizontal. To ensure that the text is in an ideal format for OCR, we can perform a perspective transform. After removing all the noise to isolate the text, we can perform a morph close to combine individual text contours into a single contour. From here we can find the rotated bounding box using cv2.minAreaRect and then perform a four point perspective transform using imutils.perspective.four_point_transform. Continuing from the cleaned mask, here's the results:

Mask -> Morph close -> Detected rotated bounding box -> Result

Output with the other image

Updated code to include perspective transform

import cv2
import pytesseract
import numpy as np
from imutils.perspective import four_point_transform

pytesseract.pytesseract.tesseract_cmd = r"C:\Program Files\Tesseract-OCR\tesseract.exe"

# Load image, convert to HSV, color threshold to get mask
image = cv2.imread('1.png')
hsv = cv2.cvtColor(image, cv2.COLOR_BGR2HSV)
lower = np.array([0, 0, 0])
upper = np.array([100, 175, 110])
mask = cv2.inRange(hsv, lower, upper)

# Morph close to connect individual text into a single contour
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (5,5))
close = cv2.morphologyEx(mask, cv2.MORPH_CLOSE, kernel, iterations=3)

# Find rotated bounding box then perspective transform
cnts = cv2.findContours(close, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
rect = cv2.minAreaRect(cnts[0])
box = cv2.boxPoints(rect)
box = np.int0(box)
cv2.drawContours(image,[box],0,(36,255,12),2)
warped = four_point_transform(255 - mask, box.reshape(4, 2))

# OCR
data = pytesseract.image_to_string(warped, lang='eng', config='--psm 6')
print(data)

cv2.imshow('mask', mask)
cv2.imshow('close', close)
cv2.imshow('warped', warped)
cv2.imshow('image', image)
cv2.waitKey()

Note: The color threshold range was determined using this HSV threshold script

import cv2
import numpy as np

def nothing(x):
    pass

# Load image
image = cv2.imread('2.png')

# Create a window
cv2.namedWindow('image')

# Create trackbars for color change
# Hue is from 0-179 for Opencv
cv2.createTrackbar('HMin', 'image', 0, 179, nothing)
cv2.createTrackbar('SMin', 'image', 0, 255, nothing)
cv2.createTrackbar('VMin', 'image', 0, 255, nothing)
cv2.createTrackbar('HMax', 'image', 0, 179, nothing)
cv2.createTrackbar('SMax', 'image', 0, 255, nothing)
cv2.createTrackbar('VMax', 'image', 0, 255, nothing)

# Set default value for Max HSV trackbars
cv2.setTrackbarPos('HMax', 'image', 179)
cv2.setTrackbarPos('SMax', 'image', 255)
cv2.setTrackbarPos('VMax', 'image', 255)

# Initialize HSV min/max values
hMin = sMin = vMin = hMax = sMax = vMax = 0
phMin = psMin = pvMin = phMax = psMax = pvMax = 0

while(1):
    # Get current positions of all trackbars
    hMin = cv2.getTrackbarPos('HMin', 'image')
    sMin = cv2.getTrackbarPos('SMin', 'image')
    vMin = cv2.getTrackbarPos('VMin', 'image')
    hMax = cv2.getTrackbarPos('HMax', 'image')
    sMax = cv2.getTrackbarPos('SMax', 'image')
    vMax = cv2.getTrackbarPos('VMax', 'image')

    # Set minimum and maximum HSV values to display
    lower = np.array([hMin, sMin, vMin])
    upper = np.array([hMax, sMax, vMax])

    # Convert to HSV format and color threshold
    hsv = cv2.cvtColor(image, cv2.COLOR_BGR2HSV)
    mask = cv2.inRange(hsv, lower, upper)
    result = cv2.bitwise_and(image, image, mask=mask)

    # Print if there is a change in HSV value
    if((phMin != hMin) | (psMin != sMin) | (pvMin != vMin) | (phMax != hMax) | (psMax != sMax) | (pvMax != vMax) ):
        print("(hMin = %d , sMin = %d, vMin = %d), (hMax = %d , sMax = %d, vMax = %d)" % (hMin , sMin , vMin, hMax, sMax , vMax))
        phMin = hMin
        psMin = sMin
        pvMin = vMin
        phMax = hMax
        psMax = sMax
        pvMax = vMax

    # Display result image
    cv2.imshow('image', result)
    if cv2.waitKey(10) & 0xFF == ord('q'):
        break

cv2.destroyAllWindows()