Abstract
Based on spiking neural network and colour visual processing mechanism, a hierarchical network is proposed to extract multi-features from a colour image. The network is constructed with a conductance-based integrate-and-fire neuron model and a set of receptive fields. Inspired by visual system, an image can be decomposed into multiple visual image channels and processed in hierarchical structures. The firing rate map of each channel is computed and recorded. Finally, multi-features are obtained from firing rate map. Simulation results show that the proposed method is successfully applied to recognize the target with a higher recognition rate compared with some other methods.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
