chicio's profile - activity

Hi moster. Yes it seems to work. I'm storing it using the FileStorage and YAML format structure contained in OpenCV framework http://docs.opencv.org/modules/core/doc/xml_yaml_persistence.html. I'm saving the vector of mat that contains the training descriptor for ORB in a yaml file generated by a OS X application. Then I use this file in a video recognition app for iPhone/iPad. Everything seemes fine. Thank you.

If I generate the training descriptors using ORB on OS X and I save them using FileStorage in a file, can I use them in an iOS app to feed a FLANN based matcher?

I'm trying to implement a flann based matcher and use it with ORB. How can get it in OpenCV? Now I'm using brute force hamming matching. If I undestood well, LSH has better performance related to Brute force matching. Is it right?

Hi GilLevi. I read your post and try to get good matches following your advice of get the matches with the minimum distance. With a MAX DISTANCE of 40 it seems to work well. Now i'm thinking of a way to avoid to reload the descriptor matcher every time. Is it that possible? Are there other way to check if a match is a good one (I read somewhere about ratio, but i can't find it in the matches)?

Hi GilLavi. Yes, I need some link to improve my theoretic background. In particular I need to understand how can I recognized if some matches are "good" matches. In SURF it is possible to calculate the distance between two matches getting the minimum distance * n (I get this on opencv documentation). How can get the good matches in ORB?

Thank you for your answer. Did you know if there's a sample of descriptor in OpenCV library or somewhere? I'm reading documentation about ORB and I see it uses hamilton distance so i think that ORB implentation in opencv need something related to this fact (i mean focused data structure). Can you help me?

Hi everyone,

I want to recognize in a video if an object is contained (IPHONE APP). I have a lot of different object in the training set (300+) and they will grow in the future. Following the example contained in the library (matching_to_many_images.cpp) and others on the opencv doc web site I was able to write a simple application that recognize if one of 2 training images are in the current video frame. I'm using SURF feature detector and FLANN as a matcher. Using this method i noticed that the load and training of the matcher is too slow. Here is a snippet of my code:

/******* Load images *********/
UIImage *object1Image = [UIImage imageNamed:@"ticket_medium"];
UIImage *object2Image = [UIImage imageNamed:@"magazine"];
Mat object1;
Mat object2;
UIImageToMat(object1Image, object1);
UIImageToMat(object2Image, object2);

cvtColor(object1, object1, CV_BGR2GRAY);
cvtColor(object2, object2, CV_BGR2GRAY);

trainImages.push_back(object1);
trainImages.push_back(object2);

/*****Detect keypoints*******/
featureDetector = FeatureDetector::create("SURF");
featureDetector->detect(trainImages, trainKeypoints);

/*****Compute descriptor*****/
descriptorExtractor = DescriptorExtractor::create("SURF");
descriptorExtractor->compute(trainImages, trainKeypoints, trainDescriptors);

/*****prepare matcher*****/
descriptorMatcher = DescriptorMatcher::create("FlannBased");

/******train descriptor******/
descriptorMatcher->add(trainDescriptors);
descriptorMatcher->train();

Is there a way to improve the speed of the matcher training? Are there alternative way to avoid loading and training the matcher every time I launch the application? To training the matcher I have to load every time the training image and, for each one, extract keypoints and calculate the relative descriptor, adding other extra time and slowing the application down. Can I avoid this? Do i have to save the some of the data in the DB? Which format i have to choose?