Title :
Analysis of hierarchically-temporal dependencies for handwritten symbols and gestures recognition
Author :
Bolotova, Yulia ; Spitsyn, Vladimir
Author_Institution :
Department of Computing Science, Institute of Cybernetics, Tomsk Polytechnic University, Tomsk Russia
Abstract :
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.
Keywords :
Gabor filters; genetic algorithms; handwritten character recognition; object recognition; Canny filter; Gabor filter; additional clustering; genetic algorithm; gestures recognition; handwritten symbols; hierarchical data dependencies; hierarchical temporal memory model; image preprocessing; object recognition task; spatial pooling; temporal data dependencies; temporal grouping algorithm; Algorithm design and analysis; Biological system modeling; Character recognition; Clustering algorithms; Gesture recognition; Training; Vectors; gesture recognition; hierarchical temporal memory; symbols recognition; temporal grouping;
Conference_Titel :
Strategic Technology (IFOST), 2012 7th International Forum on
Conference_Location :
Tomsk
Print_ISBN :
978-1-4673-1772-6
DOI :
10.1109/IFOST.2012.6357628