Automatic design of pulse coupled neurons for image segmentation

Authors:
Henrik Berg;Roland Olsson;Thomas Lindblad;José Chilo
Affiliations:
Faculty of Computer Sciences, Østfold University College, N-1757 Halden, Norway;Faculty of Computer Sciences, Østfold University College, N-1757 Halden, Norway;Royal Institute of Technology, Department of Physics, S-10961 Stockholm, Sweden;University of Gävle, S-80176 Gävle, Sweden
Venue:
Neurocomputing
Year:
2008

Citing 20
Cited 6

Digital image processing (2nd ed.)

Digital image processing (2nd ed.)
Original Contribution: Principal components, minor components, and linear neural networks

Neural Networks
Inductive functional programming using incremental program transformation

Artificial Intelligence
A high-performance, portable implementation of the MPI message passing interface standard

Parallel Computing
Self-organizing maps

Self-organizing maps
Image object signatures from centripetal autowaves

Pattern Recognition Letters
Patterns from the sky: satellite image analysis using pulse coupled neural networks for pre-processing, segmentation and edge detection

Pattern Recognition Letters
Normalized Cuts and Image Segmentation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
Evolution and Optimum Seeking: The Sixth Generation

Evolution and Optimum Seeking: The Sixth Generation
Image Processing Using Pulse-Coupled Neural Networks

Image Processing Using Pulse-Coupled Neural Networks
Efficient Graph-Based Image Segmentation

International Journal of Computer Vision
Motion Layer Extraction in the Presence of Occlusion Using Graph Cuts

IEEE Transactions on Pattern Analysis and Machine Intelligence
Supervised tensor learning

Knowledge and Information Systems
Feature linking via synchronization among distributed assemblies: Simulations of results from cat visual cortex

Neural Computation
Adaptive integrated image segmentation and object recognition

IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews
An adaptive neuro-fuzzy system for automatic image segmentation and edge detection

IEEE Transactions on Fuzzy Systems
PCNN models and applications

IEEE Transactions on Neural Networks
Perfect image segmentation using pulse coupled neural networks

IEEE Transactions on Neural Networks
Object detection using pulse coupled neural networks

IEEE Transactions on Neural Networks

Electronic Nose Ovarian Carcinoma Diagnosis Based on Machine Learning Algorithms

ICDM '09 Proceedings of the 9th Industrial Conference on Advances in Data Mining. Applications and Theoretical Aspects
An Automatic Parameter Adjustment Method of Pulse Coupled Neural Network for Image Segmentation

ICANN '09 Proceedings of the 19th International Conference on Artificial Neural Networks: Part I
Automated synthesis of control algorithms from first principles

IROS'09 Proceedings of the 2009 IEEE/RSJ international conference on Intelligent robots and systems
Image fusion using self-constraint pulse-coupled neural network

LSMS/ICSEE'10 Proceedings of the 2010 international conference on Life system modeling and simulation and intelligent computing, and 2010 international conference on Intelligent computing for sustainable energy and environment: Part III
Letters: Automatic image segmentation based on PCNN with adaptive threshold time constant

Neurocomputing
Using automatic programming to generate state-of-the-art algorithms for random 3-SAT

Journal of Heuristics

Quantified Score

Hi-index	0.01

Visualization

Abstract

Automatic Design of Algorithms through Evolution (ADATE) is a program synthesis system that creates recursive programs in a functional language with automatic invention of recursive help functions and self-adaptive optimization of numerical values. We implement a neuron in a pulse coupled neural network (PCNN) as a recursive function in the ADATE language and then use ADATE to automatically evolve better PCNN neurons for image segmentation. Our technique is generally applicable for automatic improvement of most image processing algorithms and neural computing methods. It may be used either to generally improve a given implementation or to tailor that implementation to a specific problem, which with respect to image segmentation for example can be road following for autonomous vehicles or infrared image segmentation for heat seeking missiles that are to distinguish the heat source of the target from flares.