Using image morphological techniques, locate the broken locations

Question

Can someone please guide the steps/the operation to be performed to construct this image and detect the broken fence position of the Image.

1. Thresholding the image to a binary image : to convert the input image to a binary image
2. Inverting the image : inverting it to get a black background and white lines
3. Dilation with SE one unit of the fence structure
4. Apply Erosion
5. Bitwise-and masks together: retrieve the original back- and foreground the image is inverted by subtracting the bitwise_or from 255
6. Constructed Image - Original Image will give us the position of the broken fence

Will this solution work ?

Answer 1

Depends what you call locate.

After large horizontal erosion and binarization: