Geerten
  • Member for 10 years
  • Last seen more than 1 year ago
What are some free alternatives to SIFT/ SURF that can be used in commercial applications?
28 votes

There is a relatively new method, you might want to look into: BRISK, Binary Robust Invariant Scalable Keypoints: In this paper we propose BRISK, a novel method for keypoint detection, description ...

View answer
What Are the Limitations of a Canny Edge Detector?
Accepted answer
19 votes

From my experience, the following points are limitations: The result is binary. You sometimes need a measure of 'how much' the edge qualifies as an edge (e.g. intensity image coming from a Sobel ...

View answer
Resources for an introduction to computer vision
Accepted answer
6 votes

If (from the comments) you are interested in an introduction to computer vision (for the difference, see Question on difference between CV and IP), you could take a look at the introductory course of ...

View answer
Libraries for Voice Activity Detection (Not Speech Recognition)
6 votes

There are open source implementations in the Sphinx and Freeswitch projects. I think they are all energy based detectors do won't need any kind model. Sphinx 4 (Java but it should be easy to port to ...

View answer
Best way of segmenting veins in leaves?
6 votes

When using Canny edge detection (in Halcon), with alpha being 1, and the low threshold 8 and the high threshold 13 (on a scale of 1-255), I get the following result: With tweaking of the parameters, ...

View answer
List of possible image features for content based image retrieval
6 votes

There is also a book that bundles a set of papers related to this topic. It's called Principles of Visual information Retrieval.

View answer
What Is the Relationship Between a Kalman Filter and Polynomial Regression?
5 votes

Kalman filtering gives multiple predictions for the next state, where an extrapolation of a regression would not. The Kalman filters are also focused on including noise factors (based on Gaussian ...

View answer
What is the link between the homography computed over 2 images and the homography computed over the same images upside down?
Accepted answer
5 votes

I think when looking at the formula for the homography matrix: $$ H_{ba} = R - \frac{tn^T}{d} $$ where $R$ is the rotation matrix by which $b$ is rotated in relation to $a$; $t$ is the translation ...

View answer
Topological skeleton matching techniques
Accepted answer
4 votes

I think you should look/google in the direction of graph matching. This is because you can represent your skeleton as a graph by creating nodes at endpoints and crossings, and creating edges for the ...

View answer
Pattern recognition and Machine Learning reference
Accepted answer
3 votes

Another good book is: - Pattern Recognition by Theodoridis and Koutroumbas It's about classifiers, features and clustering in the context of pattern recognition. It contains all the mathematical ...

View answer
What are some good signal and image processing blogs worth following?
2 votes

Machine Vision 4 Users is a very practical blog on machine vision. Regular posts on camera's, lenses, software, lighting and the wole package that is necessary when developing machine vision setups. ...

View answer
Camera calibration/pin hole camera model and working out 3d position
2 votes

You can't know the 3d position of the second point. It can be any of the points on the ray from your center of the camera until infinity. You can do the following: Create a predefined 3d space ...

View answer
how to extract features from this image ? what are the suitable features to be selected?
2 votes

You can try using template matching on the resulting image of your image processing operations. So you have a database of these images, there comes a new image in, you process it, and you find the ...

View answer
Triangulation from set of points from left camera
2 votes

If you could know the 3D position from only one camera, what would be the use of stereo vision? You need to match two points found in both cameras, and then you can use epipolar geometry to ...

View answer
Image Processing Prior to Feature Detection
Accepted answer
1 votes

A possibility would be to do a simple edge detection (such as Laplace), and use the mean intensity of the result as a basis for the threshold for the Harris corners. When you have low contrast, you ...

View answer