CODEWITHSUNDEEP
pythonopencvtesseract
radix
radix

Reputation: 188

Python and OpenCv Implementation to encode text on Image Itself

I have a small code in python that detects text from Images as:

import cv2


image = cv2.imread("sample.jpg")
gray = cv2.cvtColor(image,cv2.COLOR_BGR2GRAY) # grayscale
_,thresh = cv2.threshold(gray,150,255,cv2.THRESH_BINARY_INV) # threshold
kernel = cv2.getStructuringElement(cv2.MORPH_CROSS,(3,3))  
dilated = cv2.dilate(thresh,kernel,iterations = 13) # dilate
_, contours, hierarchy =  cv2.findContours(dilated,cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_NONE) # get contours

# for each contour found, draw a rectangle around it on original image
for contour in contours:
    # get rectangle bounding contour
    [x,y,w,h] = cv2.boundingRect(contour)

    # discard areas that are too large
    if h>300 and w>300:
        continue

    # discard areas that are too small
    if h<40 or w<40:
        continue

    # draw rectangle around contour on original image
    cv2.rectangle(image,(x,y),(x+w,y+h),(255,0,255),2)

    # write original image with added contours to disk  
    cv2.imwrite("contoured.jpg", image)

So the output is a new image that has rectangles over the detected text. I have also a function that encodes the text from a static image and shows the encoded result onto the console, the function is shown below:

from pytesseract import image_to_string


val_1 = sys.argv[1]
text =  image_to_string(Image.open(''+val_1+''))

def encode(key, string):
    encode = []
    for i in xrange(len(string)):
        key_c = key[i % len(key)]
        encoded_c = chr(ord(string[i]) + ord(key_c) % 256)
        encode.append(encoded_c)
    encoded_string = "".join(encode)
    return base64.urlsafe_b64encode(encoded_string)

encry =  encode(key,text)
#print encry

So for eg.If I feed it an image containing text it will extract the text ,encode it (if we give it a key) and print the encoded string onto a console.However is it possible to encode the text on top of the image itself instead of printing it on the console.

Upvotes: 4

Views: 1250

Answers (2)

sinecode
sinecode

Reputation: 794

Yes, it is possible.

You need the image containing the text and the coordinates of the area with the text. Then you could use the OpenCV function putText().

In order to do this you have to apply some changes to your implementation. You have two different options:

  • Peform the OCR in every rectangle containing the text, so you should do something like this:

    import cv2
from pytesseract import image_to_string


# ..various image operations..

# for each contour found, draw a rectangle, perform OCR in that rectangle and write the result on the image
for contour in contours:
    # get rectangle bounding contour
    [x,y,w,h] = cv2.boundingRect(contour)

    # discard areas that are too large
    if h>300 and w>300:
        continue

    # discard areas that are too small
    if h<40 or w<40:
        continue

    # draw rectangle around contour on original image
    cv2.rectangle(image,(x,y),(x+w,y+h),(255,0,255),2)

    # get the image area with the text
    text_image = image[y:y+h, x:x+w]
    # perform OCR
    text = image_to_string(text_image)
    # encode the text with your function
    encry = encode(key, text)
    # write the encoded text on the image
    cv2.putText(image, encry, (x,y), cv2.FONT_HERSHEY_SIMPLEX, 4, (255,255,255), 2, cv2.LINE_AA)
    • Alternatively you could perform one single OCR operation on the entire image and then analyze the coordinates of the text recognized. You should use something like pytesseract.image_to_boxes or pytesseract.image_to_data.

I want to clarify that I've not tested the code, so probably there may be some inaccuracies.

Upvotes: 1

GPPK
GPPK

Reputation: 6666

If you have the text (which you do) and you have a location that it needs to go (which you do) then it shouldn't be too difficult to add the text over the image.

OpenCV provides the PutText function:

https://docs.opencv.org/3.1.0/dc/da5/tutorial_py_drawing_functions.html

Here is an example:

font = cv2.FONT_HERSHEY_SIMPLEX
2 cv2.putText(img,'OpenCV',(10,500), font, 4,(255,255,255),2,cv2.LINE_AA)

Upvotes: 0

Related Questions