I was looking for a purely statistical method for image segmentation and found many, e.g. Hidden Markov Random Fields with EM algorithm. But it seems to me that these methods are nowadays completely turned down by neural nets. Is it right or is there still something where statistical methods can excel in image segmentation?


closed as primarily opinion-based by Sycorax, user158565, whuber Jan 14 at 14:44

Many good questions generate some degree of opinion based on expert experience, but answers to this question will tend to be almost entirely based on opinions, rather than facts, references, or specific expertise. If this question can be reworded to fit the rules in the help center, please edit the question.


It is common practice to use some sort of graphical model on-top of the segmentations output by a CNN to fine-tune and output the final prediction. (See "DeepLab" models)

Also, aren't neural networks statistical models as well?

  • $\begingroup$ They are very different when you are writing the grant application or applying for a job. ;) $\endgroup$ – usεr11852 Jan 12 at 19:50
  • $\begingroup$ Thank you for the response! I usually think of neural nets as a more black-box thing than pure statistical algorithms as K-means etc. But you can surely correct me :) $\endgroup$ – Septinel Jan 13 at 21:57

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