The two features are fused at the recognition stage.
In the recognition stage, we first follow the simple template matching strategy with the nearest neighbor classifier.
Even though a small set of short examples were used in the training stage, all bit strings of any length were classified correctly in the online recognition stage.
Within an integrated vision/recognition system, CONFIGR posits an initial recognition stage which identifies figure pixels from spatially local input information.
The detection technique is based on Haar-like features, whereas eigenimages and PCA are used in the recognition stage of the system.
This leads to realizing an algorithmic cognition recognition model, where the cognition stage establishes a reference model of a normal/healthy class and the recognition stage involves discriminating whether a given test sample belongs to a normal class or not.
Originally designed to fill-in missing contours in an incomplete image such as a dashed line, the same CONFIGR system connects and segments sparse dots, and unifies occluded objects from pieces locally identified as figure in the initial recognition stage.
Second, we apply a refinement of the Multi-Task Sparse Learning (MTSL) framework to exploit the relationships among multiple shared tasks generated by changing the regularization parameter during the recognition stage.
In the pattern recognition stage, a shape description language is used for each border of the joint surface to detect the locations of erosions and osteophytes on hand radiographs.
Finally, the recognition stage segments a spatio-temporal volume of data using the obtained trajectories, and compute a video descriptor called Volumetric Spatiograms of Local Binary Patterns (VS-LBP), which is delivered to a bank of SVM classifiers to perform the gesture recognition.
In the recognition stage, images were photographed at 4 fps.
