Revision history [back]

Image matching is done by using one of the two following approaches:

1. Bags of Words: http://docs.opencv.org/modules/features2d/doc/object_categorization.html?highlight=bow#
2. Feature point matching: http://docs.opencv.org/modules/features2d/doc/common_interfaces_of_feature_detectors.html

You can look at the tutorials on how to do feature matching with feature points:

http://docs.opencv.org/doc/tutorials/features2d/table_of_content_features2d/table_of_content_features2d.html#table-of-content-feature2d

Or there are tons of guides online for BoW matching like this one:

http://www.morethantechnical.com/2011/08/25/a-simple-object-classifier-with-bag-of-words-using-opencv-2-3-w-code/