This forum is disabled, please visit https://forum.opencv.org
| 2015-10-01 12:12:12 -0600 | received badge | ● Enthusiast |
| 2015-09-23 05:40:10 -0600 | commented answer | [Solved] Linking on Mac OSX I used it earlier with a cascade classifier I had. It worked fine. Can you detail a little better the error obtained? |
| 2015-09-21 13:51:39 -0600 | answered a question | [Solved] Linking on Mac OSX I'm not sure how you've installed and added opencv to your project. But I've followed what's stated in here: [youtube - opencv + xcode] (https://www.youtube.com/watch?v=XJeP1...) and everything turned out ok. Cheers |
| 2015-09-21 08:40:05 -0600 | received badge | ● Supporter (source) |
| 2015-09-21 07:43:18 -0600 | answered a question | Template Matching for Coins I am working with a very similar problem. Basically, I'm working with SVM, BoVW, SIFT and some basic preprocessing. I've got some pretty good results so far. My biggest problem is with darker coins. Since it's a part time work, I am not evolving quickly, so the papers cited by @albertofernandez will be good for me too. Cheers |
| 2015-09-18 07:40:24 -0600 | commented question | SVM on iOS versus OSX not at all! Since i'm a new user I found weird that it didn't appear at first. thanks! |
| 2015-09-18 07:31:48 -0600 | asked a question | OpenCV SVM on IOS versus Computer I am developing an app that recognizes certain objects based on pictures obtained from the camera. I am using as features: SIFT + RGB histogram. I've ran a SVM on my computer (OSX) on 200+ images and saved a XML with both the SVM model and BOVW descriptors. When I test my model on the computer for resubstitution error, I get a perfect score. When I load these files on iOS, my classifier won't get a single image correctly classified. I've tested with the same pictures used for training too, but still got a 0% accuracy. Both opencv versions are 3.0 Ideas? |
| 2015-09-18 07:31:47 -0600 | asked a question | SVM on iOS versus OSX Hello there, I am developing a coin recognizer for iOS and I'm using opencv for feature extraction and SVM training. So far, I managed to train my classifier on my computer (OSX) using opencv 3.0, SIFT extraction and SVM. Resubstitution error rates are perfect (i.e. 100% accuracy). Moving to the iOS end, I am loading both my BoVW descriptors and SVM model from the bundle (xml files) and using them for recognition. Nevertheless, I am getting 0% accuracy. Things already verified: - SVM, when loaded on iOS, possesses the same parameters obtained by the OSX training step (grid search went well I believe). - BoVW descriptors look good too. I'm thinking about a floating point error or something like that? Regards, Jean |