Re:Computer Vision: Algorithms and Applications (2010)
by emanuelev on Tuesday September 27, 2016 @06:12AM
(#12588421)
Regardless the impact machine learning techniques are having on the field, I still think is valuable to know and understand what are the classic methods that they are allegedly replacing.
[ Parent
| on HN ]
Re:Computer Vision: Algorithms and Applications (2010)
by rsp1984 on Tuesday September 27, 2016 @08:10AM
(#12588944)
It is actually not about "classic" vs. "modern". A lot of what's described in the book is as relevant as ever.
Mostly what's changed is that what used to be heuristics and hand-crafted features is now getting replaced by proper learned models. Also some generative models are getting replaced discriminative models since deep learning does a very good job in creating those.
Re:Computer Vision: Algorithms and Applications (2010)
by stared on Tuesday September 27, 2016 @06:50AM
(#12588577)
Sure. Just it's nice to know which pieces are:
- considered obsolete (e.g. complicated and nasty, and still outclassed by NNs),
- building blocks of current techniques,
- provided inspiration for current techniques,
- are still state of the art.