Mean Shift: A Robust Approach Toward Feature Space Analysis
IEEE Transactions on Pattern Analysis and Machine Intelligence
Reconstruction of Patterns from Noisy Inputs Using Morphological Associative Memories
Journal of Mathematical Imaging and Vision
Journal of Mathematical Imaging and Vision
IEEE Transactions on Pattern Analysis and Machine Intelligence
Circular road signs recognition with soft classifiers
Integrated Computer-Aided Engineering - Artificial Neural Networks
Hi-index | 0.00 |
In this paper a hybrid neuro-fuzzy system for the real-time recognition of the road-signs is presented. For tracking an improvement to the continuously adaptive mean shift method is proposed. It consists in substitution of the probabilistic density for the especially formed membership function. Classification of binary pictograms of the detected signs is done with the kernel morphological neural network which is robust to noise, missing data, and small geometrical deformations of the patterns.