Shin's profile - activity

Is it possible to combine different features in a classification task? I read about training SVMs for each kind of collected descriptors and then use a weighted summation of the results to actually integrate/combine information, but how it should be done in practice?.

I know this question has been asked before, but i was wondering if with the current version of OpenCV (release 2.4) has changed anything.

Should i prefer the C++ or Python interface? Are there any big differences between them? Can you easily translate opencv code from one language to the other? And finally, can i use this book (amazon->Learning OpenCV) to get started anyway or are there any better ones?

Thank you.

I think that's it. Thank you for everything :-).

@unxnut: So, if for example, i'm using SURF features, i could try varying the hessian threshold?

Number of clusters (first step is a Bag-of-words classification approach)

For the "apple" classifier (a 1-vs-all classifier) i take precision and recall for different k values. I then plot them like in http://i40.tinypic.com/3145rme.jpg

I'm actually a little bit confused. Could you elaborate more or make an example? If i'm following your reasoning, you mean Recall = # True Positives / # Total Positives, but total should indeed be equal to (#True Positives + #False Negatives), which corresponds to my definition from earlier.

@unxnut: Precision = TP/(TP+FP), Recall = TP/(TP+FN)

@unxnut Hi unxnut. Thank you for your comment. I was wondering if you could take a quick look to my confusion matrixes. You can find a screenshot of my spreadsheet here http://tinypic.com/r/qssdxw/5

Is this

http://i39.tinypic.com/2n0cw2.jpg">

a possibile outcome for a precision-recall graph or you think i'm doing something wrong? (The blue line is relative to a one-step classifier, the other line refers to the same classifier with the difference that this time a second step is added in the classification process).

Hello there, i recently implemented a Bag of Words categorization algorithm based on the one described in this paper http://217.109.185.161/layout/set/print/content/download/20785/148346/file/2004_010.pdf.

All works well, but i'd like to measure accuracies of the classifiers using ROC curves or, perhaps, precision-recall graphs.

I can easily get the confusion matrix for each of the classifiers but i don't know what parameter i should change to get more points and actually plot the curves.

Could someone please explain this to me?

@Guanta: thank you. I have seen that example, but i am interested in mixing different kinds of features, combining descriptors from, say, sift AND surf, in single vectors and then getting bow descriptors. Is this approach feasible or i'm saying something wrong ?

@Guanta: Thank you for your answer. Actually the BoW approach using local features was my first thought but I haven't found examples on how to use BoW with multiple kind of features. I'm sorry to ask but could you provide minimal sample code?

@StevenPuttemans : Thank you for your answer. I'd like to use a global descriptor for a color image in combination with a global descriptor for a depth image (from which i can get a point cloud) and combine them in a single descriptor vector. My ultimate goal is to feed the descriptor vectors to a support vector machine. For this task, i want the descriptor to be scale and rotation invariant. Any suggestion?

Thank you. Well, i was reading them using a cv::Mat object of type CV_16UC1. I'd like to know if some scaling operation is needed (considering that these are indeed kinect depth images) and that most opencv functions work with CV_8U matrixes.

Is there any OpenCV implementation of a global image features detector?

I need to use the dataset at http://www.informatik.uni-freiburg.de/~spinello/RGBD-dataset.html and i'd like to know how to correctly read in the depth images using opencv.

I've uploaded one of these depth images here: http://bitshare.com/files/fqil8g7s/seq0_0000_0.pgm.html

Thank you.