Asynchronous Cellular Operations on Gray Images Extracting Topographic Shape Features and Their Relations
This work addresses pattern recognition challenges in image analysis by providing methods to handle distortions, though it appears incremental in its approach.
The paper tackles the problem of extracting robust shape descriptors from gray images by introducing asynchronous cellular automata operations that produce stable wave-front states, and demonstrates their application in character classification and gray pattern decomposition.
A variety of operations of cellular automata on gray images is presented. All operations are of a wave-front nature finishing in a stable state. They are used to extract shape descripting gray objects robust to a variety of pattern distortions. Topographic terms are used: "lakes", "dales", "dales of dales". It is shown how mutual object relations like "above" can be presented in terms of gray image analysis and how it can be used for character classification and for gray pattern decomposition. Algorithms can be realized with a parallel asynchronous architecture. Keywords: Pattern Recognition, Mathematical Morphology, Cellular Automata, Wave-front Algorithms, Gray Image Analysis, Topographical Shape Descriptors, Asynchronous Parallel Processors, Holes, Cavities, Concavities, Graphs.