Die Suche ergab 19 Treffer

von ampelmann
23. Mai 2014 15:19
Forum: Allgemein
Thema: LaTex Corporate Design Mac 10.9 findet Schriften nicht
Antworten: 1
Zugriffe: 1010

LaTex Corporate Design Mac 10.9 findet Schriften nicht

Hallo zusammen, ich habe nun schon auf verschiedensten Wegen versucht, das Corporate Design der Uni für Latex auf meinem Mac OS 10.9 zu installieren. Habe mich genau an die Anleitung gehalten, aber egal ob ich $ sudo updmap-sys --enable Map 5ch.map $ sudo updmap-sys --enable Map 5fp.map $ sudo updma...
von ampelmann
13. Jul 2013 21:22
Forum: Computer Vision
Thema: A4 Problem 2
Antworten: 1
Zugriffe: 725

A4 Problem 2

Hi there, I have some questions concerning the fundamental-matrix-task: 1. I tried to build my preliminary F with all right-value columns where the corresponding singular value is really close to 0 (so that matlab actually displays 0). However, the rank of the resulting F-matrix is not always >2. So...
von ampelmann
1. Jul 2013 20:41
Forum: Computer Vision
Thema: Assignment 3 - Problem 2 Loading images
Antworten: 3
Zugriffe: 866

Re: Assignment 3 - Problem 2 Loading images

I split first airplanes and then motorbikes randomly into half so my distribution is maybe a bit less random then if you take all images at ones and split. this is how i understood the task and don't think it's a problem - still getting some variation if i run it multiple times.
von ampelmann
30. Jun 2013 21:51
Forum: Computer Vision
Thema: Assignment 3 B.2 'Compute and compare'
Antworten: 2
Zugriffe: 623

Re: Assignment 3 B.2 'Compute and compare'

Thanks, sounds good :)
von ampelmann
30. Jun 2013 12:01
Forum: Computer Vision
Thema: Assignment 3 B.2 'Compute and compare'
Antworten: 2
Zugriffe: 623

Assignment 3 B.2 'Compute and compare'

Hi, short question: What exactly shall we reformulate, compute and compare? What I understood so far is: reformulated (1), computed posteriors with the most right part of the formula (the one with the products of (µ/Cj)^n(i,m)) and compared the posteriors of class 0 and class 1, adding a short comme...
von ampelmann
28. Jun 2013 18:35
Forum: Computer Vision
Thema: Ex 3.2 - Comparing error rates
Antworten: 8
Zugriffe: 1870

Re: Ex 3.2 - Comparing error rates

Ok, so I will spend some time on speeding up my code later. However, the output should be right by now so I will do the vectorization part when I am done with the rest. Thanks for that help, feel a bit encouraged now :)
von ampelmann
28. Jun 2013 18:22
Forum: Computer Vision
Thema: Ex 3.2 - Comparing error rates
Antworten: 8
Zugriffe: 1870

Re: Ex 3.2 - Comparing error rates

Hi, thanks for that reply! I kind of have the same steps (even though I need some more lines ;) ). Just to clarify: You are working with feature vectors (128x1), right? So I have ~4800 feature vectors in total. For all these vectors I compute distances to the 50 means and do all the min, move, recom...
von ampelmann
28. Jun 2013 16:47
Forum: Computer Vision
Thema: Ex 3.2 - Comparing error rates
Antworten: 8
Zugriffe: 1870

Re: Ex 3.2 - Comparing error rates

Hi, how do you solve k-means in 4-6 seconds?? I am working on it for days now, being really frustrated. It takes about 30-50 iterations (then it stops no matter what so it don't run forever). However, finding a cluster for each of the multiple thousand feature vectors (120 images * 10 and more vecto...
von ampelmann
28. Jun 2013 16:42
Forum: Computer Vision
Thema: compute histogram
Antworten: 2
Zugriffe: 735

Re: compute histogram

I just computed histogram-values for each image. with 120 images, i have an output-histogram 120x50. for example in histogram(20,10), you find the value how many feature vectors of image 20 were assigned into cluster 10. That's how I understood it and I really hope it's not totally wrong cause I am ...
von ampelmann
26. Jun 2013 16:27
Forum: Computer Vision
Thema: Assignment 3 2A - NaN values
Antworten: 2
Zugriffe: 558

Re: Assignment 3 2A - NaN values

Hi, thanks for that quick reply. And I really don't know what I've changed, but now it works fine... Maybe it was the coffee break.
von ampelmann
26. Jun 2013 15:31
Forum: Computer Vision
Thema: Assignment 3 2A - NaN values
Antworten: 2
Zugriffe: 558

Assignment 3 2A - NaN values

Hi, my extract_feature class returns some training data that contains "NaN" values. What could cause this? I guess I am doing something wrong with applying SIFT, because my harris-feature points are correct (checked visually).I apply sift on the feature points. Is there anything I might have missed?...
von ampelmann
26. Jun 2013 09:54
Forum: Computer Vision
Thema: Assignment 3 - Problem 2 - K-Means
Antworten: 5
Zugriffe: 884

Re: Assignment 3 - Problem 2 - K-Means

Thank you, think that helped :)
von ampelmann
25. Jun 2013 21:25
Forum: Computer Vision
Thema: Assignment 3 - Problem 2 - K-Means
Antworten: 5
Zugriffe: 884

Re: Assignment 3 - Problem 2 - K-Means

So we're supposed to implement our own k-means, right? however, I am still a bit confused: are the mean-values vectors (because x_j is a vector, isn't it? It's a 128 dimensional point...)? so to choose the minimum, I would compare the distances per dimension or simply sum them up and compare sums? A...
von ampelmann
24. Jun 2013 18:18
Forum: Computer Vision
Thema: Ex 3.2A
Antworten: 1
Zugriffe: 624

Ex 3.2A

Hi, I am working on part A of exercise 3.2 right now. However, if I apply the harris detector we got on an image, I do get really small values which never exceed any threshold bigger than 0.005. The image is converted with im2double, because if I keep it in unit8, I get an error in the harris-code. ...
von ampelmann
12. Jun 2013 16:19
Forum: Computer Vision
Thema: Ex 2.1
Antworten: 4
Zugriffe: 924

Re: Ex 2.1

Tank you, I think that helped :)

Zur erweiterten Suche