Matching Algorithm2

[protruser]

Discussed in #39

^{Originally posted by protruser December 15, 2024}
I separated the bill into three parts like 02, 03 and 06. But it is not work well, and hard to detect it.
Due to the hidden images, it still gives an error like

res_06 = cv2.matchTemplate(roi_06, template_06, cv2.TM_CCOEFF_NORMED)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
cv2.error: OpenCV(4.10.0) D:\a\opencv-python\opencv-python\opencv\modules\imgproc\src\templmatch.cpp:1175: error: (-215:Assertion failed) *img.size().height <= *templ.size().height && *img.size().width <= *templ.size().width in function 'cv::matchTemplate'

we have to solve this problem of how to separate the bill and get features of hidden images

This is my idea.

You can share the comments at any time!!

[gogog01-29-2021]

I've checked it

[ksj2001]

With this AI-generated image, I don't get it.
Can you explain in more detail?

[protruser]

With this AI-generated image, I don't get it. Can you explain in more detail?

I separate the bill into three parts. There is three parts but the program still make an error in part06. So I'm considering deleting part06, and only focus part02 and part03.

Because regarding this pictures, there are more parts that we have to detect it. But if we only focus 'Hidden person' and '1000 letter', then we have to fix algorithm again.

src : https://github.com/mannmi/KoreanWonDetection/issues/37

There are more information that you can find in this url.