Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Review of Pulse-Coupled Neural Network Applications in Computer Vision and Image Processing

Nurul Rafi, Pablo Rivas

TL;DR

This paper surveys pulse-coupled neural networks (PCNNs), biologically inspired spiking models of visual cortex, focusing on their mathematical formulation, variants, and applications in computer vision. It systematically covers the feeding, linking, and pulse-generation mechanisms, along with dynamic thresholds, and surveys PCNN-based methods across image segmentation, edge detection, medical imaging, image fusion, image compression, object recognition, remote sensing, and noise removal. The review highlights variants such as SRG-PCNN, SPCNN, M-PCNN, and NSST-SF-PCNN, illustrating how time-based pulses yield perceptual features that can improve vision tasks, while also noting computational cost and parameter sensitivity as key challenges. The authors argue that PCNNs can serve as effective perceptual pre-processing elements in vision pipelines and identify opportunities for automatic parameter tuning, chaotic-dynamics exploration, and closer integration with modern learning and neuroscience insights.

Abstract

Research in neural models inspired by mammal's visual cortex has led to many spiking neural networks such as pulse-coupled neural networks (PCNNs). These models are oscillating, spatio-temporal models stimulated with images to produce several time-based responses. This paper reviews PCNN's state of the art, covering its mathematical formulation, variants, and other simplifications found in the literature. We present several applications in which PCNN architectures have successfully addressed some fundamental image processing and computer vision challenges, including image segmentation, edge detection, medical imaging, image fusion, image compression, object recognition, and remote sensing. Results achieved in these applications suggest that the PCNN architecture generates useful perceptual information relevant to a wide variety of computer vision tasks.

A Review of Pulse-Coupled Neural Network Applications in Computer Vision and Image Processing

TL;DR

This paper surveys pulse-coupled neural networks (PCNNs), biologically inspired spiking models of visual cortex, focusing on their mathematical formulation, variants, and applications in computer vision. It systematically covers the feeding, linking, and pulse-generation mechanisms, along with dynamic thresholds, and surveys PCNN-based methods across image segmentation, edge detection, medical imaging, image fusion, image compression, object recognition, remote sensing, and noise removal. The review highlights variants such as SRG-PCNN, SPCNN, M-PCNN, and NSST-SF-PCNN, illustrating how time-based pulses yield perceptual features that can improve vision tasks, while also noting computational cost and parameter sensitivity as key challenges. The authors argue that PCNNs can serve as effective perceptual pre-processing elements in vision pipelines and identify opportunities for automatic parameter tuning, chaotic-dynamics exploration, and closer integration with modern learning and neuroscience insights.

Abstract

Research in neural models inspired by mammal's visual cortex has led to many spiking neural networks such as pulse-coupled neural networks (PCNNs). These models are oscillating, spatio-temporal models stimulated with images to produce several time-based responses. This paper reviews PCNN's state of the art, covering its mathematical formulation, variants, and other simplifications found in the literature. We present several applications in which PCNN architectures have successfully addressed some fundamental image processing and computer vision challenges, including image segmentation, edge detection, medical imaging, image fusion, image compression, object recognition, and remote sensing. Results achieved in these applications suggest that the PCNN architecture generates useful perceptual information relevant to a wide variety of computer vision tasks.
Paper Structure (14 sections, 15 equations, 2 figures, 1 table)

This paper contains 14 sections, 15 equations, 2 figures, 1 table.

Table of Contents

  1. Introduction
  2. Pulse Coupled Neural Network Design
  3. Process and Mathematical Definitions
  4. Parameter Settings
  5. Applications of PCNN
  6. Image Segmentation
  7. Edge Detection
  8. Medical Imaging
  9. Image Fusion
  10. Image Compression
  11. Object Recognition
  12. Remote Sensing
  13. Noise Removal
  14. Conclusions

Figures (2)

  • Figure 1: Basic Structure of a Pulse-Coupled Neural Network.
  • Figure 2: Examples of pulses of PCNN. The top row is the initial iteration, the middle row is the 10-th pulsation, and the bottom row is the result after 30 pulses.