Analysis of hierarchically-temporal dependencies for handwritten symbols and gestures recognition

This work represents a biologically inspired approach to object recognition based on analysis of hierarchical and temporal data dependencies. The article describes the hierarchical temporal memory model (HTM) and its optimization for object recognition task. Optimization includes Gabor and Canny filter image preprocessing, which makes the model suitable for handwritten symbols and gestures recognition; using of additional clustering on the stage of spatial pooling, a new proposed temporal grouping algorithm increases the overall recognition accuracy of the model; a new genetic algorithm was designed for searching the optimal parameters of the model.