Questions tagged [feature-detection]
The feature-detection tag has no usage guidance.
15
questions
0
votes
0
answers
15
views
Understanding Scale-space extrema detection in SIFT
Why do we say that minima in the scale-space domain make for good key points? It makes sense for maxima to be considered, but why do we consider it if it's a minima?
This does not cohere with my ...
0
votes
0
answers
21
views
Where is the Hessian matrix computed in SURF?
I understood that, in SIFT, the Hessian matrix is used to remove edges from previously detected keypoints. Hence, if I understood well, in SIFT the Hessian matrix is computed only in the locations ...
1
vote
0
answers
24
views
Feature extraction for IRIS recognition
What are types for feature extraction in iris recognition? How can I divide it on types which detect phase, edge, etc.?
1
vote
0
answers
20
views
ORB Implementation, Scale Pyramid, rFAST
Reading this ("ORB: An efficient alternative to SIFT or SURF") paper, I am not certain how they use the scale pyramid.
It says it is created and FAST feature detectors are employed at every ...
1
vote
1
answer
80
views
Corner detector vs feature detector
In the literature, I see "corner detector" and "feature detector" are interchangeably used for these methods e.g. Harris, Shi-Tomasi, FAST, etc.
What is the difference between a ...
0
votes
1
answer
57
views
Feature detector vs dense detector
What is the difference between a feature detector and a dense detector in computer vision? Are they the same or a subset of one another?
For the following algorithms (implemented in OpenCV), which of ...
2
votes
1
answer
80
views
Palmprint Identification - Why do we align the images before we use the Fourier Transform?
I was reading the paper PALMPRINT IDENTIFICATION BY FOURIER TRANSFORM by WENXIN LI, DAVID ZHANG and ZHUOQUN XU about identifying persons based on an image of their palm.
The first step in their ...
0
votes
0
answers
23
views
Finding the differences(using features, not subtraction) in order to find differences in signals
I have a question. Let’s say I have two signals (discretely represented as arrays), $S_1$ and $S_2$ as shown below. $S_1$ has a similar form to $S_2$. If the signals are subtracted, $S_2-S_1$, they ...
1
vote
0
answers
37
views
KLT tracker, reject tracked occluded points
I want to use KLT tracker for a visual odometry application. Thus, I only want to track object features. Currently I'm using OpenCV's implementation ...
0
votes
1
answer
34
views
What are the ranges of values for each audio feature/descriptor?
I need to normalize some audio feature measurements I've done with the software Wolfram Mathematica.
Coming from a non signal processing background, I have some difficulties understanding what ...
1
vote
1
answer
55
views
Is there any way to do 3D (Voxel Data) feature detection?
In the 2D image processing, there are ways to find and match features of the image (like corner of the edges). However, I could not find the equivalent of that in the 3D-voxel data (Here voxel means a ...
1
vote
2
answers
685
views
Scratch Detection On Noisy Textured Surface
I wish to extract long thin scratches from the noisy background image.I have tried several ways such as stacking smoothed image with input image to remove some of the noisy background patch before ...
0
votes
1
answer
64
views
How to make series circle shift invariant
I have a series of numbers. They may be integer, floating, or ...
2
votes
2
answers
549
views
How to extract features of individual spikes in non-negative signal?
I have data of non-negative (in the sense there's no signal below baseline) spiking waveforms, which are in the form of a 1D array of numbers:
Spikes that cross some threshold are considered real ...
4
votes
2
answers
5k
views
ORB Algorithm: What Is Intensity Centroid?
So, I am reading a paper about ORB: An Efficient Alternative to SIFT or SURF and it happens to calculate the direction of corner from it center . According to Rosin the author of the paper;moments of ...