Biologically Inspired Approaches to Automated Feature Extraction and Target Recognition Speaker: Yi-Chun Ke Adviser: Bo-Chi Lai
outline Introduction Method conclusion
Introduction computational models of biological vision and learning Vision models – long-range grouping – figure/ground segmentation memory models – bottom-up – top-down
Introduction cognitive and neural computations to technological applications – open-source code – user-friendly – integrated vision and recognition systems
Recognition – Adaptive Resonance Theory (ART) training – winner-take-all coding testing – distributed coding
Method Vision – Boundary Contour System and Feature Contour System (BCS/FCS) long-range boundary completion featural filling-in
conclusion ATR is colsing human cognitive information processing new information fusion methodologies are not limited to the image domain – medical data – improve marketing