Stack Overflow
Stack Overflow

Questions tagged [feature-detection]

Feature detection is a process in computer vision that aims to find visual features within the image with particular desirable properties. Detected features can be points, image regions or continuous curves in the image. Interesting properties can include invariance to noise, perspective transformations, or properties interesting for specific usages (e.g. tracking).

Feature detection is a process in computer vision that aims to find visual features within the image with particular desirable properties.

Detected features are some subsection of the image, and can be:

  • points (e.g. Harris corners)
  • connected image regions (e.g. DoG or MSER regions)
  • continuous curves in the image

Interesting properties can include invariance to noise, perspective transformations and viewpoint changes (camera translation and rotation), scaling (for use in visual feature matching), or properties interesting for specific usages (e.g. visual tracking).

Important information about visual features can include:

  • coordinates in the image
  • radius of the visual feature
  • scale (octave) of the image on which the feature has been extracted

After detecting the feature with some feature detection algorithm, it is usually described by a descriptor vector (several known descriptors are used today) for the purposes of visual feature matching, while the feature's position in the image can be used directly for application in tracking.

909 questions
7
votes
1 answer

Harris-Laplacian-Detector: Corner- and Blob-Detector?

I have a question regarding the Harris-Laplacian-Detector introduced by Mikolajczyk et al. With the Harris you search maximas of "cornerness" within each particular scale and then with the Laplacian you search maximas of "blobness" over the scales…
steckl
  • 404
  • 8
  • 16
7
votes
3 answers

Feature extraction from neural networks

I'm doing simple recognition of letters and digits with neural networks. Up to now I used every pixel of letter's image as the input to the network. Needless to say this approach produces networks which are very large. So I'd like to extract…
kyku
  • 5,892
  • 4
  • 43
  • 51
6
votes
2 answers

How to I compute matching features between high resolution images?

I am trying to match SIFT features between two images which I have detected using OpenCV: sift = cv2.xfeatures2d.SIFT_create() kp, desc = sift.detectAndCompute(img, None) The images both seem to contains lots of features, around 15,000 each, shown…
nickponline
  • 25,354
  • 32
  • 99
  • 167
6
votes
1 answer

How to detect good features for rotationally aligning microscope images to a template

I'm working on a project to automatically rotate microscope image stacks of a fluid experiment so that they are lined up with images of the CAD template for the microfluidic chip. I am using the OpenCV package in Python for image processing. Having…
rarnason
  • 91
  • 4
6
votes
2 answers

How to store Hierarchical K-Means tree for a large number of images, using Opencv?

I am trying to make a program that will find similar images from a dataset of images. The steps are extract SURF descriptors for all images store the descriptors Apply knn on the stored descriptors Match the stored descriptors to the query image…
AquaAsh
  • 176
  • 1
  • 5
  • 12
6
votes
2 answers

SIFT Object Matching in Python

I'm trying to follow this tutorial with my own images.However, the results I get are not exeacty what I'd exepct. Am I missing something here, or is SIFT just not a good enough solution in this case? Thanks alot. import numpy as np import cv2 from…
Alex
  • 85
  • 1
  • 8
6
votes
2 answers

Euclidean distance transform in tensorflow

I would like to create a tensorflow function, that replicates the euclidean distance transform of scipy for each 2-dimensional matrix in my 3-dimensional tensor. I have a 3-dimensional tensor, where the third axis is representing a one-hot encoded…
Gatlack
  • 138
  • 10
6
votes
1 answer

OpenCV, Python: How to use mask parameter in ORB feature detector

By reading a few answers on stackoverflow, I've learned this much so far: The mask has to be a numpy array (which has the same shape as the image) with data type CV_8UC1 and have values from 0 to 255. What is the meaning of these numbers, though? Is…
Victor Odouard
  • 1,345
  • 3
  • 15
  • 28
6
votes
2 answers

how to detect if the screen is capacitive or resistive in an Android device?

I am developing an application that will behave slightly different depending on the type of screen. Is there any way to detect it?
biquillo
  • 6,469
  • 7
  • 37
  • 40
6
votes
1 answer

How to get points coordinate position in the face landmark detection program of dlib?

There is one example python program in dlib to detect the face landmark position. face_landmark_detection.py This program detect the face feature and denote the landmarks with dots and lines in original photo. I wonder if it is possible to obtain…
randy Pen
  • 171
  • 1
  • 2
  • 9
6
votes
0 answers

Detect browser support of external svg for the use element?

I am looking for a way to test if a browser can have an external svg reference in the use element: This works in most modern browsers, but does not work in browsers like IE11 or Edge.…
KevBot
  • 17,900
  • 5
  • 50
  • 68
6
votes
1 answer

How do EmguCV detectors relate to EmguCV DescriptorExtractors?

Reading EmgCV docs cant quite understand: what detectors can be used with which DescriptorExtractors? Here it is said: You can use it with the FREAK descriptor that is scale invariant. Just replace the BriefDescriptorExtractor with Freak and it…
DuckQueen
  • 772
  • 10
  • 62
  • 134
6
votes
2 answers

Does Convolutional Neural Network possess localization abilities on images?

As far as I know, CNN rely on sliding window techniques and can only indicate if a certain pattern is present or not anywhere in given bounding boxes. Is that true? Can one achieve localization with CNN without any help of such techniques?
Barış Geçer
  • 73
  • 1
  • 5
6
votes
3 answers

Multiple tracking in a Video

I m working on small image processing assignment where I need to track 4 red color object. I got how to track single one. I want to know what is the best approach to track more than one point. There are 4 points which are positioned to form a…
user3767923
6
votes
3 answers

Advice for algorithm choice

I have to do a project that tries to scan the shape of the vehicles and detect what type of vehicle it is , the scanning will performed with a sensors called “vehicle scanner” they are just 50 beams of lights, each beam with receptor and emission as…
agustin
  • 104
  • 5
1 2 3
…
60 61