Questions tagged [cv.computer-vision]

Theoretical questions about Computer Vision

Filter by
Sorted by
Tagged with
-3
votes
1answer
50 views

Could you run a computer using a different base to base 1 (binary) [closed]

I was wondering whether you could run a computer of a different system to binary using different degrees of certainty (more that just true and false - maybe true, false and possibly)?
2
votes
1answer
254 views

Converting a pictorial representation of a directed graph to a adjacency matrix

I am not sure if there is a better forum to ask this question, so I will try here. Consider an image, say in .jpeg format, representing a directed graph, with nodes. Is there an algorithm, be it a ...
0
votes
0answers
128 views

Algorithm to go from a picture (or pictures) of a string in space, to a piecewise-linear representation of the curve

Say you have a knotted-up string or, as in this case, USB cable: I am wondering to what extent there are algorithms that could turn a picture like this (or a succession of pictures of the same object)...
2
votes
1answer
439 views

What is the difference between standard SIFT descriptor and upright SIFT descriptor?

I am conducting a research on the topic of mobile location recognition and recently I have reached the issue of extracting discriminative features. I've read that for upright images is strongly ...
5
votes
1answer
774 views

Computational Complexity of Computer Vision Problems

What is the computational complexity of computer vision problems (reconstruction, detection, etc.)? Are these problems NP-complete? Are they NP-hard? In most cases this will boil down to determining ...
1
vote
0answers
634 views

Need help understanding Cumulative Match Score (CMS) Curves

I have been reading some papers regarding face recognition, and I often see statistics depicting the performance of the algorithms in the form of CMS or ROC curves. I do understand what ROC curves are,...
0
votes
2answers
697 views

Advantages of ANN classifiers over the AdaBoost

So what are the advantages of ANN classifiers over the AdaBoost or Boosting algorithm?
1
vote
1answer
1k views

What is the significance of abstract linear algebra in machine learning/computer vision research?

I am a computer science research student working in application of Machine Learning to solve Computer Vision problems. Since, lot of linear algebra(eigen-values, SVD etc.) comes up when reading ...
1
vote
1answer
227 views

What is the most Accurate way of Determining an Object's Color? [closed]

I have written a computer program that can detect coins in a static image (.jpeg, .png, etc.) using some standard techniques for computer vision (Gaussian Blur, thresholding, Hough-Transform etc.). ...
3
votes
2answers
799 views

What are some applications of computational geometry towards computer vision?

I'm interested in both of these topics independently, and wondering some good applications of comp geom within the domain of vision. What are some nice applications and potential projects of comp ...
1
vote
0answers
78 views

represent tiles in lower dimensionality

For a naive feature detection algorithm, I'll divide the image in 8x8 grayscale tiles. I want to be able to represent the 64 pixels of each tile in a lower dimensional form. Each tile should be an ...
2
votes
1answer
106 views

Cleaning images in order to perform feature detection

I have a set of images (e.g. cars) and trying to perform feature detection using SIFT (actually, SIFT modification - A-SIFT, which is more robust to affine transformations) and I'm getting an ...
1
vote
0answers
123 views

When was first line detection algorithm created and when line detection problem was posed?

I wonder when was first line detection algorithm created (first used in practice and refrenced by any publications) and when line detection problem was posed (I know it can look like generaal edge ...
10
votes
4answers
355 views

Recovering the slope of a digitized line

Has there been any work on recovering the slope of a line segment from its digitization? One can't do this with perfect accuracy, of course; what one wants is a method of deriving from a digitized ...
7
votes
2answers
465 views

Using SAT for Computer Vision tasks

Could anyone please point to both introductory and advanced papers/books showing how to use SAT technology to solve Computer Vision tasks (e.g. edge detection, object recognition, facial recognition, ....