2015-07-17 13:04:01 -0600 | answered a question | How to find a "contour" of 3d object? It is not possible to get a 3D image from a set of images taken from the same point of view, but different focal lengths. Unless you misused technical terms and wanted to say something different. |
2015-06-19 03:25:12 -0600 | commented question | Haar Training got stuck At the beginning of all cycles _offset.x and _offset.y are both 0. When they come back to be both 0 it means that all possible negative windows have been checked. |
2015-06-18 15:33:32 -0600 | commented question | Haar Training got stuck The source code of traincascade/imagestorage.cpp in function NegReader::nextImg() doesn't provide a mechanism to throw an error in such a case. But I have to say that stage 6 is very soon to be stuck for this reason, unless there are only very very few images. |
2015-06-18 07:02:17 -0600 | commented question | Haar Training got stuck How many negative images have you got? If the algorithm is not able to collect 4000 negative windows from them it will run forever. |
2015-06-18 02:04:17 -0600 | commented question | Haar Training got stuck There is nothing bad with your parameters (you could increase maxDepth, but this shouldn't be the reason you are stuck). What do you mean: "I got stuck at stage 6"? Do you get some error message? Or the training is completed at stage 6? How do you get all your positive samples? Are they artificial (i.e. obtained from just very few of them) or really 1000 different samples? Please show what is the output on the screen. |
2015-06-17 12:10:12 -0600 | received badge | ● Necromancer (source) |
2015-06-17 11:25:36 -0600 | answered a question | HAAR training fails at different stages |
2015-06-17 07:27:49 -0600 | commented question | Haar Training got stuck Please add more information |
2015-05-26 05:43:10 -0600 | commented question | How to do OpenCV in Windows Application? The way I've followed to do the same thing you are asking here is adviced against by most programmers. Anyway I want to share my experience. I used interop, that is I divided my application in a Opencv/c++ module and a c# one. I'm much more productive with visual studio with c# and at the same time I want to keep the more delicate and efficient part completely written in c++, which is the original language of OpenCv. I have no problem because I have described clearly a few functions in the c++ library that allow me the needed level of interaction and there are not bottlenecks. Of course this approach can only work if you know in advance what are this few functions and you don't want a complete control over the framework. Otherwise you can go with a wrapper as Emgu. |
2015-05-26 05:23:46 -0600 | commented question | how to call image from memory of program? It is not clear here what you mean by "other program". What level of communication there is with this program? I suppose you have no control over the "other program" and you only know the size of the image, its format and a pointer to its data, On windows machines, if you have administrator provileges you can create a Mat header with the informations you have about the image and then copy the imagedata from the first program to your program through |
2015-05-18 02:30:52 -0600 | commented question | Does opencv_traincascades give consistent results over time? Did you interrupt the training process and then resumed it? |
2015-05-11 16:18:09 -0600 | answered a question | Does opencv_traincascades give consistent results over time? Have you ever heard about chaos theory and deterministic chaos? there is a call to cv::parallel_reduce, based on TBB. EDIT I myself tried to reproduce the behaviour I observed same time ago (non-deterministic results during training), but I was not able to reproduce those conditions. Too much time has gone since then (now I use a really random mechanism to extract negatives). |
2015-05-10 15:13:21 -0600 | commented answer | advice for a hand tracking algorithm I agree. In image processing there is no difference than in robot localisation. Anyway kalman filters relies on strong assumptions about the motion of the object (for example linear with constant velocity), techniques like particle filters are more general and fitted for tracking object inside images. |
2015-05-09 02:42:23 -0600 | commented question | Neuronal network predict access violation How many samples are you using for training? |
2015-05-09 02:33:32 -0600 | commented question | Existing something like Microsofts How-Old by OpenCV I think that such a task requires a huge amount of samples to train the estimator. Probably Microsfot itself, with all its means, should increase the number of samples, because it is still inaccurate. |
2015-05-09 02:25:08 -0600 | commented question | Detection of texture portions in a image As far as I know, there is not already implemented code in Opencv to do such a job. You should write your own detector. I think that wavelets based techniques are the most fitted for this and wavelets are not difficult to calculate in Opencv, |
2015-05-09 02:21:51 -0600 | commented answer | advice for a hand tracking algorithm You said it right, "can be improved". In the sense the trajectory can be softened, but the main problem of tracking remains. |
2015-05-01 14:23:47 -0600 | commented question | Emotions from profile faces I've just sent an email to him. |
2015-05-01 02:44:08 -0600 | commented question | Emotions from profile faces @berak, I've tested the face detector and it seems great! I've looked for some information about the algorithm, but I've mainly found links to their own website. Furthermore, incredibly there are only 2 citations reported by google scholar. How did you know about it? Anyway, I think that a self-implementation code of the ideas reported on the paper are not prohibited. |
2015-05-01 02:07:44 -0600 | commented question | Emotions from profile faces @berak, do you know if "pico" is patented? |
2015-04-29 14:13:49 -0600 | commented answer | Help me with the opencv_traincascade training I don't know neuroph, but I think that training a NN would be a good choice. (A NN with multiple outputs, each one corresponding to a class to be recognized) |
2015-04-28 15:07:07 -0600 | commented answer | Help me with the opencv_traincascade training Unless you: 1) gather much many samples, 2) decide in advance a criteria to crop the area of the flower, 3) possibly restrict your detection goal only to flower from a certain point of view, 4) understand that you cannot use adaboost to classifie flowers, but just to detect where a generic flower is located, you will never obtain a decent result. |
2015-04-26 15:35:02 -0600 | commented answer | Help me with the opencv_traincascade training Am I the only one to notice that -numPos was set to 1521 out of 10,000 available samples? |
2015-04-26 14:19:01 -0600 | answered a question | Cascade training for closed eye detection It would be better using totally random images, but nobody prevent you from using some images of the open eye.
It does not surprise me that your algorithm is not able to distinguish between right and left eyes as they are very similar. |
2015-04-12 04:56:49 -0600 | commented answer | Multiple objects classification And I guess, too slow. :) |
2015-04-12 03:34:09 -0600 | answered a question | Multiple objects classification Yes, traincascade can be used to detect objects of one particular type. The classical way to achieve your goal is to train multiple classifiers, use them in turn for detection over each image and put the results together. A large RAM doesn’t matter. For this purpose you need much a good CPU (number of cores and GHz). |
2015-04-07 10:18:29 -0600 | received badge | ● Enthusiast |
2015-04-06 12:40:24 -0600 | received badge | ● Good Answer (source) |
2015-04-06 12:40:24 -0600 | received badge | ● Enlightened (source) |
2015-04-04 06:53:06 -0600 | edited answer | traincascade detections with output score for precision recall curves As you know, we can image this kind of classifier as a function which assigns a couple of values to every window it gets as inputs: a rejectLevels, that is the integer value representing the stage where it was eventually rejected, and levelWeights, the double value the boosting algorithm outputs (the one thresholded to pass the next level of the cascade). What you experienced depends only on the little number of samples used to train the classifier. |