A Neural Markovian Multiresolution Image Labeling Algorithm
This addresses image labeling for computer vision systems, offering a concurrent approach that may provide valuable information for higher-level vision, though it appears incremental as it builds on existing MRF methods.
The paper tackles the problem of image labeling by proposing the MCV algorithm, which concurrently performs segmentation and classification using a Markov random field model and outputs a sequence of partitions, with evaluation showing very good results.
This paper describes the results of formally evaluating the MCV (Markov concurrent vision) image labeling algorithm which is a (semi-) hierarchical algorithm commencing with a partition made up of single pixel regions and merging regions or subsets of regions using a Markov random field (MRF) image model. It is an example of a general approach to computer vision called concurrent vision in which the operations of image segmentation and image classification are carried out concurrently. While many image labeling algorithms output a single partition, or segmentation, the MCV algorithm outputs a sequence of partitions and this more elaborate structure may provide information that is valuable for higher level vision systems. With certain types of MRF the component of the system for image evaluation can be implemented as a hardwired feed forward neural network. While being applicable to images (i.e. 2D signals), the algorithm is equally applicable to 1D signals (e.g. speech) or 3D signals (e.g. video sequences) (though its performance in such domains remains to be tested). The algorithm is assessed using subjective and objective criteria with very good results.