Abstract
The conventional multilayer self-organizing neural network (MLSONN) architecture [89] suffers from several limitations as far as the extraction and segmentation of multilevel and color images are concerned. A multilevel version of the standard sigmoidal activation function was introduced in [33, 34, 232, 233] for inducing multiscaling capability in the functionality of the architecture, without increasing the network complexity in the process.
Full Text
Published Version
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 call