|PARP Research Group||Universidad de Murcia|
The group Image processing contains all the image processing functionality offered by the QVision, most of which is built on top of the Intel Performance Primitives (IPP) library. The IPP library provides, for example, a very large set of linear, non-linear, morphological and color filters, among many other general purpose image processing and computer vision algorithms, which are all highly optimized to run very fast in Intel processors. QVision defines a convenient QT style set of C++ wrapper functions on top of the IPP, in order to use the IPP functionality from QVision applications in an intuitive and straightforward manner.
But this group also contains several medium-level image processing functions developed by the programmers of the QVision library themselves, and which are not part of the Intel IPP libraries. Many of these functions obtain some kind higher-level data structures (image features) from the raw images (image features are pieces of information which can be extracted from an image, and are relevant for solving a given computer vision task). By now, QVision includes several interesting image feature extraction algorithms yet (MSER, borders, corners, contours, etc...), but we keep constantly adding new methods and classes in this group.