Die Suche ergab 21 Treffer

von franzel
24. Jun 2013 18:33
Forum: Computer Vision
Thema: Ex 3.2A
Antworten: 1
Zugriffe: 630

Re: Ex 3.2A

Hi,

i don't have the code in front of me right now, but im2double() automatically scales the image to [0,1]. Try to typecast it with double(x) instead. Then, it should be double in the range of [0,255]. If that does not fix it, let me know and i will investigate further.

Regards,
Thorsten
von franzel
14. Jun 2013 14:50
Forum: Computer Vision
Thema: Ex 2.3
Antworten: 2
Zugriffe: 1828

Re: Ex 2.3

Hi, i wrote an reply, but apparently i forgot to press send and now it is lost. :roll: Anyways, lustiz's reply pretty much answers your question. Of course it makes only sense to do NMS for each pixel. Non overlapping windows would not be able to suppress surrounding values consistently. Think about...
von franzel
12. Jun 2013 17:41
Forum: Computer Vision
Thema: Assignment 2 - Two questions
Antworten: 1
Zugriffe: 691

Re: Assignment 2 - Two questions

Hi, 1) Does it make sense to do "standard" convolution here? Elementwise matrix operations on differently sized matrices are going to be difficult, right? For boundary handling "symmetric" is a good choice, but in principle they all have different pros/cons. 2) You can set the range yourself by imsh...
von franzel
10. Jun 2013 18:40
Forum: Computer Vision
Thema: Ex 2.1
Antworten: 4
Zugriffe: 926

Re: Ex 2.1

Hi, i'm soory i obviously didn't get where you were coming from exactly. So yes you could solve this with a vector (-1,0,1) for a filter with size 3. However you are note quite right with your solution for filter size 4. This is obviously not equally spaced. Think about a grid of pixels (5x5). Where...
von franzel
10. Jun 2013 14:01
Forum: Computer Vision
Thema: Ex 2.1
Antworten: 4
Zugriffe: 926

Re: Ex 2.1

Hi, i'm not really sure why you write the first derivative (central difference) there. You are supposed to create a isotropic gaussian as depicted in lecture 3 slide 17. Think about the goal that we try to achieve here and what the actual purpose for convolution with a gaussian filter is. I hope thi...
von franzel
6. Mai 2013 11:53
Forum: Computer Vision
Thema: 1st Assignment - Orga
Antworten: 1
Zugriffe: 625

Re: 1st Assignment - Orga

The first assignment will be out soon. All material will be available in Moodle and on the webpage. Additionally, we will announce these matters over the mailing list.

Kind regards
Thorsten
von franzel
22. Jan 2013 12:01
Forum: Computer Vision 2
Thema: A4P2 edges4connected
Antworten: 4
Zugriffe: 872

Re: A4P2 edges4connected

1. The order is not of relevance, since you build a sparse matrix (sparse()) out of this list. This is basically an intermediate step to building the "pairwise" variable. 2. You basically create an adjacency matrix, where only the upper triangle is used. The GCO library assumes undirected edges as s...
von franzel
18. Jan 2013 11:28
Forum: Computer Vision 2
Thema: A4P2 edges4connected
Antworten: 4
Zugriffe: 872

Re: A4P2 edges4connected

Hi,

your solution is correct. it contains all the edges of a (3,2) image in a list.

You should implement this without any loops. Loops are only allowed when implementing iterative procedures like iterating over labels in alphaexpansion(...).

Regards,
Thorsten
von franzel
12. Dez 2012 14:56
Forum: Computer Vision 2
Thema: Assignment 3
Antworten: 1
Zugriffe: 742

Re: Assignment 3

Thanks for your hint. Assignment 3 is now visible in Moodle.

Regards,
Thorsten
von franzel
5. Dez 2012 11:15
Forum: Computer Vision 2
Thema: Assignment 2 - Problem 1 - Markov Blanket
Antworten: 2
Zugriffe: 903

Re: Assignment 2 - Problem 1 - Markov Blanket

Robert is right regarding the definition. The formal definitions from both books ("Probabilistic Graphical Models: Principles and Techniques", "Computer vision:models, learning and inference") suggest that the markov blanket of variable X does not include X itself. However, it is convention (c.f. "C...
von franzel
16. Nov 2012 22:57
Forum: Computer Vision 2
Thema: A1 P3 likelihood
Antworten: 2
Zugriffe: 564

Re: A1 P3 likelihood

Did you already answer 3.3? What is the reason for computing the log instead of working with the actual probability densities? Does the negative log-likelihood give you a reasonable results? Think about what numbers are actually multiplied, when you compute the gaussian likelihood. Once you look at ...
von franzel
16. Nov 2012 14:44
Forum: Computer Vision 2
Thema: A1 P1.2
Antworten: 2
Zugriffe: 480

Re: A1 P1.2

The joint distribution is given as p(v, w, x, y, z). It has 5 variables. Now you should marginalize p(v, w, x, y, z) with respect to w and z. After that you should marginalize over x. You should interpret the first part of the first sentence as: "You are given a distribution p(v, w, x, y, z) over 5 ...
von franzel
15. Nov 2012 16:01
Forum: Computer Vision 2
Thema: A1 P2
Antworten: 2
Zugriffe: 578

Re: A1 P2

You are absolutely right with your interpretation.

Regards,
Thorsten
von franzel
13. Jul 2009 23:27
Forum: Archiv
Thema: Exercise 2
Antworten: 2
Zugriffe: 1093

Re: Exercise 2

Exercise2 is done and can be picked up at Carola Eichel's Office.
The corresponding points will be entered into webreg in the next hour.
von franzel
17. Jun 2009 20:35
Forum: Archiv
Thema: Exercise 2
Antworten: 2
Zugriffe: 1093

Re: Exercise 2

Exercise 2 is now available on the course website. This exercise is due before June 30, 2pm.

Zur erweiterten Suche