(-215:Assertion failed) !_src.empty() in function 'cv::cvtColor' with cv::imread

I am trying to recognize text from an image to then have the text outputted; however, this error spits out:

Traceback (most recent call last): File "C:/Users/Benji's Beast/AppData/Local/Programs/Python/Python37-32/imageDet.py", line 41, in print(get_string(src_path + "cont.jpg") ) File "C:/Users/Benji's Beast/AppData/Local/Programs/Python/Python37-32/imageDet.py", line 15, in get_string img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) cv2.error: OpenCV(3.4.4) C:\projects\opencv-python\opencv\modules\imgproc\src\color.cpp:181: error: (-215:Assertion failed) !_src.empty() in function 'cv::cvtColor'

The image resolution is 1371x51. I have tried changing the "/" on src_path to "\" but that didn't work. Any ideas?

Here is my code:

import cv2
import numpy as np
import pytesseract
from PIL import Image
from pytesseract import image_to_string

# Path of working folder on Disk
src_path = "C:/Users/Benji's Beast/Desktop/image.PNG"

def get_string(img_path):
    # Read image with opencv
    img = cv2.imread(img_path)

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

    # Apply dilation and erosion to remove some noise
    kernel = np.ones((1, 1), np.uint8)
    img = cv2.dilate(img, kernel, iterations=1)
    img = cv2.erode(img, kernel, iterations=1)

    # Write image after removed noise
    cv2.imwrite(src_path + "removed_noise.png", img)

    #  Apply threshold to get image with only black and white
    #img = cv2.adaptiveThreshold(img, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY, 31, 2)

    # Write the image after apply opencv to do some ...
    cv2.imwrite(src_path + "thres.png", img)

    # Recognize text with tesseract for python
    result = pytesseract.image_to_string(Image.open(src_path + "thres.png"))

    # Remove template file
    #os.remove(temp)

    return result


print('--- Start recognize text from image ---')
print(get_string(src_path + "cont.jpg") )

print("------ Done -------")

I have no idea how to fix this, thanks.

Solution 1:

This means you are passing a Uninitialized variable to

> cv2.cvtColor()

After this statement:

# Read image with opencv
img = cv2.imread(img_path)

Can you try to print the img variable before passing to cv2.cvtColor() function

> print(img) or print(img.shape)

to make sure function call to read the image is successful

Solution 2:

Error: !_src.empty() in function 'cv::cvtColor means the object passed to function cvtColor is empty or say none. Here, in the following line img is none

cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

and img is result of following function -

img = cv2.imread(img_path)

The possible reasons, why img can be empty object are -

1. The image path is not correct, try absolute path and check image file extension.
2. The image file is not accessible. There could be permission issue.

To avoid this error check if img object is None, if it is not none then only pass it to cvtColor function.

img = cv2.imread(img_path)
if(img is not None):
    cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

Solution 3:

This error occurs when the image is in one format and in the python program you specify other format.

Example:

File Path= /home/user/image.jpg

but in the python program you read the image as jpeg

img = cv.imread("image.jpeg")

Then you will be facing this error

Solution 4:

If anyone came here searching this error message on Google but this error for you is for a video rather than an image, one possible reason might be you just ran out of frames to read from the video. reference

while True:
    # Capture frame-by-frame
    ret, frame = cap.read()
    # if frame is read correctly ret is True
    if not ret:
        print("Can't receive frame (stream end?). Exiting ...")
        break
    # Our operations on the frame come here
    gray = cv.cvtColor(frame, cv.COLOR_BGR2GRAY)

Using ret to check the end of the video is common practice but you may have forgotten to mention it or do the operations on the frame before checking if the frame is available or not (ret == True) like me. Cheers.