Computer Vision News - October 2016

In the above example, the first code section (//Query Image) starts by reading the image (ImRead) and detecting the feature with the Fast method (FastFeatureDetector). Other methods such as STAR, BRISK (and more) can be quickly changed and evaluated simply by renaming the object name from “FastFeatureDetector” to “ORBFeatureDetector” etc. Follows the description of those detected features performed with BriefDescriptorExtractor. Other alternative includes: BRISK, ORB and more. The second block of code (// Query Image) starts by the FannBasedMatcher (Fast Approximate Nearest Neighbor Search Library), which finds matching points. The next block DescriptorMatchFilter filters out some matches by removing non-related ones, such as far distance matching. The last block DrawMatching (implanted by QT plugin) is responsible for displaying the matching points of the two images (the query and the training image). Interactive interface In the last example we will show you an interactive interface for investigating image features. Here the image is shown on the left and on top of the image features are marks with circles. In addition, the feature points are listed with their values on the right. The feature points were detected and described by one of the point detection methods (i.e. FastFeatureDetector and BriefDescriptorExtractor). Clicking on one of the points to the left marks it with a big circle on top of the image: its values are displayed below, along with its histogram values. Computer Vision News Tool 13 Tool “It works quickly and efficiently”