Proceedings ArticleDOI
Efficient neural network implementation of morphological operations
Aldo Morales,Sung-Jea Ko +1 more
- Vol. 1658, pp 276-286
Reads0
Chats0
TLDR
This paper introduces a neural network implementation of gray scale operators, in which synaptic weights are represented by a gray scale structuring element and trained by a learning algorithm based on an optimal criterion called the overall equality index.Abstract:
This paper introduces a neural network implementation of gray scale operators. In this structure, synaptic weights are represented by a gray scale structuring element and trained by a learning algorithm based on an optimal criterion called the overall equality index. The proposed algorithm leads to a computationally simple implementation, with numerical examples to illustrate its performance.read more
Citations
More filters
Journal ArticleDOI
Adaptive Fuzzy Morphological Filtering of Impulse Noisein Images
Jinsung Oh,Luis F. Chaparro +1 more
TL;DR: A neural network implementation for fuzzy morphological operators is introduced, and by means of a training method and differentiable equivalent representations for the operators they then derive efficient adaptation algorithms to optimizethe structuring elements.
Journal ArticleDOI
A general purpose model for image operations based on multilayer perceptrons
Jenlong Moh,Frank Y. Shih +1 more
TL;DR: This paper investigates the use of multilayer perceptrons with recurrent connections as the general purpose modules for image processing in parallel architectures and provides various sets of training patterns that the system can adapt itself to the concatenated transformation.
Visual pattern recognition using neural networks
TL;DR: This research presents a novel and scalable approach called “Smart grids” that combines “smart cities” with smart grids to solve the challenge of integrating smart phones and smart grids into the physical world.
Journal ArticleDOI
Design of one-pass training algorithms for variant morphological operations
Jenlong Moh,Frank Y. Shih +1 more
TL;DR: The algorithms intend to achieve a fast-learning goal in which the morphological neurons can learn a training pattern and memorize it in exactly one training iteration.
References
More filters
Book
Adaptive pattern recognition and neural networks
TL;DR: This is a book that will show you even new to old thing, and when you are really dying of adaptive pattern recognition and neural networks, just pick this book; it will be right for you.
Journal ArticleDOI
Neurocomputations in relational systems
TL;DR: The problem of learning the connections of the structure is addressed, and relevant learning procedures are proposed, and an optimized performance index which has a strong logical flavor is proposed.
Journal ArticleDOI
From binary to grey tone image processing using fuzzy logic concepts
TL;DR: The functions of minπ and maxπ are introduced as the analogues of nearest neighbour “propagation” signals of binary images as well as extending some already well known binary processes into grey level algorithms.