Questions tagged [image-processing]

273 questions
24
votes
3 answers

What are the differences between computer vision and image processing?

What are the differences between computer vision and image processing? For example, in object recognition, what are the roles of computer vision and image processing?
gena
  • 251
  • 1
  • 2
  • 5
22
votes
3 answers

What is the difference between the fundamental matrix and the essential matrix?

Could someone, in plain english, explain the distinction between the fundamental matrix and the essential matrix in multi-view computer vision? How are they different, and how can each be used in computing the 3D position of a point imaged from…
s-low
  • 323
  • 1
  • 2
  • 5
22
votes
1 answer

2D convolution: Flipping the kernel?

Why do we need to flip the kernel in 2D convolution in the first place? What's the benefit of this? So, why can't we leave it unflipped? http://www.songho.ca/dsp/convolution/convolution2d_example.html input kernel output "First, flip the…
user1095332
  • 595
  • 2
  • 6
  • 15
12
votes
1 answer

Google DeepDream Elaborated

I've seen a few questions on this site about Deep Dream, however none of them seem to actually speak as to what DeepDream is doing, specifically. As far as I've gathered, they seem to have changed the objective function, and also changed…
12
votes
1 answer

How to detect sunshine on a photo

How would you algorithmically detect for any given photo whether the sun was shining when the picture was taken? Examples A sample from this webcam at a mountain top: Clearly the sun is shining. In this other sample it's far less obvious: One…
Marcel Stör
  • 221
  • 1
  • 5
11
votes
1 answer

Deriving the Sobel equations from derivatives

Many sites give the Sobel operators as the convolution mask for smoothing an image. However, I haven't found a single site that describes how you can derive the operators from partial first derivatives. If anyone can explain the derivation, I would…
Quanquan Liu
  • 233
  • 2
  • 9
11
votes
2 answers

Why is the laplace transform not popular for image processing convolution?

Why is the laplace transform not popular for image processing convolution? Most textbooks only conver the Fourier transforms.
user1095332
  • 595
  • 2
  • 6
  • 15
10
votes
2 answers

What is the difference between luma and luminance?

I understand the following (correct me if I'm wrong): Statements Luma as the weighted sum of RGB gamma corrected components, but luminance is the weighted sum of RGB linear components. The gamma correction has two forms: gamma compression and…
winnie99
  • 155
  • 1
  • 7
10
votes
1 answer

Recognizing waterways in an aerial photo -- polygons from edge detection images

I am trying to recognize waterways from aerial photographs (say from Google Maps). Local governments often have GIS data that says where the waterways (and roads, buildings etc) are, but the water data in them is often somewhat inaccurate, and we…
RemcoGerlich
  • 201
  • 1
  • 7
7
votes
1 answer

Computer vision: object detection with labels that are single coordinates

Are there papers in the literature that address the following object detection task ? The task can be described as follows: Given a set of images, the labels are just coordinates (x,y) that represent the object locations that we wish to detect. A…
7
votes
2 answers

What are all the differences between the Gibbs phenomenon artefects and JPEG artefacts?

I thought the Gibbs phenomenom is the result of Fourier analysis estimation (but was it Fourier Series estimation or can it also be Fourier Transform estimation?) JPEG uses the Discrete cosines Transform. A DCT is similar to a Fourier transform in…
7
votes
1 answer

Which algorithms are usable for heatmaps and what are their pros and cons

This is a cross post from Stack Overflow, and DSP at Stackexchange since I cannot really decide which part of Stackexchange is most fitting. If this is the wrong place please tell me and I'll remove the question. I have a matrix with numerical data.…
7
votes
0 answers

Space filling between random 2D lines

Note that I had asked this question in GIS forum, although it has gotten many up-votes, still has not received any answer. Hope you can break the silence, some collaboration :) Consider a region (2D) filled with lines randomly (following…
6
votes
1 answer

Summed-area table for circular range queries

A summed-area table is a data structure and algorithm for quickly and efficiently generating the sum of values in a rectangular subset of a grid [Wikipedia]. Is there any algorithm for quickly and efficiently generating the sum of values in a…
user1494080
  • 451
  • 3
  • 13
6
votes
1 answer

Bilinear Interpolation

I am trying to implement bilinear interpolation as described in the paper Spatial Tranformer Networks by Jaderberg et. al (see link to paper). They describe bilinear interpolation in Equation 5 as: $$ V_i^c = \sum_{n}^{H}\sum_{m}^{W} U_{nm}^c…
1
2 3
18 19