There are several state-of-the-art algorithms in image denoising including Non-Local Means, BM3D and so on.

I am wondering whether there is some well-known state-of-the-art algorithms in image edge detection (with reproducible code) ?

Thanks a lot for your answering.

  • $\begingroup$ Assuming there is an answer to your question--and I don't believe there is a simple answer--then that answer will be specific to an application or field. Can you provide specifics about your possible use? $\endgroup$
    – Rethunk
    Aug 10, 2014 at 18:40
  • $\begingroup$ Thanks for your comments. I suppose the image which the algorithm is applied for is just the nature images. Do you mean that the state-of-the-art edge detection method is task-specific? As to image denoising, it seems the state-of-the-art methods perform well on almost all images, not scene-specific. $\endgroup$
    – freealbert
    Aug 11, 2014 at 12:51

1 Answer 1


Despite its age, Canny Edge Detection is still a state of the art filter. The results produced by this algorithm make for it always being included in image editing software. Solid and descriptive edges that are often overly represented by other filters. It lacks the simplicity of, say, the Boolean Edge Detection, included in the paper, "Edge Detection Techniques: Evaluations and Comparisons" by Ehsan Nadernejad, Sara Sharifzadeh, Hamid Hassanpour.

The quality of Edge Detection and Segmentation filters are difficult to appraise, and algorithm speed is usually the most important consideration when implementing them.

For code and discussion, you should take your research to codeproject.com, and lookup Image Edge Detection.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.