Stamp Detection using Computer Vision and Python

Background

A friend of mine reach out and asked me whether I could write a program to detect the number of Rubber stamps in an image. Apparently, these invoice receipts will be categorized based on the number of stamps on them. Initially, I thought of building a Deep Learning Segmentation model, but soon I realized that it is not worth the effort. 

The images are generated in a controlled environment so few computer vision algorithms should do the trick. To illustrate the computer vision algorithms used in detecting the stamps, I will be using a sample image downloaded from Google as the original image is company property. The goal is to identify two stamps in the sample image.

Solution

High level solution steps are:

1. Read the image.
2. Blur & detect the edges.
3. Find all contours and remove the smaller contours.
4. Fill the area inside contours & Close the blobs.
5. Filter the stamps.

Before we start let us import the necessary packages.

1. Read the image

Read the color image using imread function. To display the image we will use Matplotlib. Matplotlib expects the color image channels to be of the order RGB, but OpenCV reads the image as BGR, so we will write a helper function for the conversion.

2. Blur & detect the edges

First, we need to convert the image to grayscale using cvtColor function. Then, we will use bilateralFilter to reduce noise in the image. Bilateral filter is preferred over Gaussian because it preserves the edges much better. Finally, we will use canny edge detector to threshold the image and detect edges. The normal canny edge detector requires two threshold parameters which is hard to tune so we will use the one from Zero-parameter, automatic Canny edge detection with Python and OpenCV

3. Find all contours and remove the smaller contours

findContours function can find all contours in the image. The outer most contours are good enough for our use case so we will use the retrieval mode RETR_EXTERNAL. CHAIN_APPROX_NONE mode is preferred as we don't want to lose any point on the contour due to approximation. To remove the unwanted smaller contours, we can filter the contours by area.

Total nr of contours found: 408

4. Fill the area inside contours & Close the blobs

Instead of working on the original binary image, we will draw the top contours on a image with black background and use this as base. Any disconnect in the contours are easier to identify when fill the area inside the contours using drawContours function.

As suspected, the top stamp has a thin black line passing through it. We need to close this blob so that the top stamp is considered as one contour instead of two different ones. Morphological Closing operation is perfect for achieving this.

5. Filter the stamps

To isolate the stamp contours, we can identify all the contours from the latest binary image and filter for contours with more than 5 points as the stamp is an ellipse.

Bonus - Highlight the identified stamps

For demo of this program, wouldn't it be cool if we can highlight only the stamped area of the image? Since we agree that it is indeed cool, let us see how we can achieve that. The steps involved are:

1. Duplicate the original image and blur the entire image.
2. Loop through the blurred image and for the points on or inside the image (using pointPolygonTest to check) we replace it with pixel values from the output image. We are using pixel values from the output image because we need the blue lines drawn over the stamps.

Conclusion

Yep, that's it for this post. You can access this notebook from here.

Comments

[Stokry]

Nice one!

[Jason C. McDonald]

Impressive!

I'm curious how you'd handle a couple of plausible additional cases, however:

1. A round or oval company logo on the form.

2. A square or rectangular stamp.

[Aravind Ramalingam]

With some sample images this is not impossible, but would require some trail and error.

1. Most probably the company logo would not change so we can filter out the logo contour by one of the options:

   • Resize the test image to your sample image size and find all contours in the test image. Make sure to not use any approximation while retreiving the contours points. Round or oval logo will have easily more than 7 or 8 points. By now we should be able find the logo contour. In the event both the logo and stamp are of same shape then we can calculate the area of the contours and identify which contour is what. If the area is also about the same, then use location. Most often or not, position of the company logo would be fixed. Compute the center of the contours and use the relative distance from center of image to identify the logo.
   • If the color of the logo is distinct from rest of the image then convert the image to HSL space and identify the logo.

2. We can find the center of the contour using the moments and when combined with the extreme points of the contour it should be easy to identify square or rectangle stamps.

Hope you find this useful.

[eknath97]

This is really one of the best guide on stamp detection. I am going to use for website beststampguide.com/ . Thanks lot for writing this detailed one on stamp detection using python.