Bug with conv2
2 次查看(过去 30 天)
显示 更早的评论
![image_2019_10_24T18_30_29_919Z.png](https://www.mathworks.com/matlabcentral/answers/uploaded_files/244893/image_2019_10_24T18_30_29_919Z.png)
Here is a sample convolution performed with the built in function conv2. Unless I am completely crazy, this is not even close to the correct answer? Based on that image and kernel, I was expecting the output to be: [3 5 4; 9 0 6; 1 7 3]. Does anyone know of issues with conv2, or have insight to share?
0 个评论
采纳的回答
Ajay Pattassery
2019-10-30
编辑:Ajay Pattassery
2019-10-30
The above output from conv2 with the argument as 'valid' is expected.
If you are computing in the paper the kernel needs to be flipped and then slid over the image I.
The resultant kernel will be
0 0 0
0 0 0
0 0 1
Then the output will be,
3 7 8
7 2 9
3 8 0
0 个评论
更多回答(1 个)
Bruno Luong
2019-10-30
The answer is correct. May be you expect the result with sliding sum with unflip kernel which is of course wrong.
0 个评论
另请参阅
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!