2016-12-14 00:16:32 -0600 | received badge | ● Popular Question (source) |
2013-07-28 16:07:13 -0600 | commented question | Opencv APPs instalation Thx for the reply and suggestion. I want to reduce because I have to build opencv in diferent pcs with different specs (some are old) and I want to reduce the build time. It seems that some packages are linked because for instance the combination that you mentioned does not build the apps |
2013-07-28 14:52:32 -0600 | asked a question | Opencv APPs instalation Hey all, I want to get a lightweight version of opencv just for training and detecting objects. What are the minimum dependencies that the installation has to meet for the opencv apps (opencv_traincascade.exe createsamples.exe .. etc.. ) to be built? Regarding the opencv cmake configuration. Shouldnt these be enough? Thx |
2013-04-19 11:20:06 -0600 | received badge | ● Nice Question (source) |
2013-01-15 05:51:12 -0600 | received badge | ● Student (source) |
2013-01-13 11:10:13 -0600 | received badge | ● Editor (source) |
2013-01-13 11:08:36 -0600 | asked a question | Traincascade implementation doubts Hey all, I have worked with cascade classifiers with opencv for some time. In order to train a classifier, I have been using opencv_haartraining because of the tutorials that I have found along the way (tutorial , faq). I know that it is a code that has little maintenance and has been declared obsolete, but it has been serving its purpose until now. I have also read the algorithm (Viola and Jones) to get more insight about the algorithm and understand its behaviour. I am tempted to change into the new version (opencv_traincascade) because of the TBB implementation that it has. I get a speedup of 4-6 times doing the same training on both algorithms, i.e. a classifier trained under the same conditions using haartraining takes 5-7 hours and with traincascade (with tbb) 50 minutes. Since i am interested on training multiple classifiers it is obvious that the traincascade is most appealing solution. But, i have been looking into the parameters, the code and the algorithm and I have found differences and left me with some doubts:
| N | HR | FA | ....... | 18| 0.999473| 0.48153| and stage 2 .... | 16| 0.999472| 0.442773| the final FA rate would be 0.48153 * 0.442773 = 0.21320848269 (based on the formula FA_rate^#stages
Thanks in advance |