Image Processing using Pulse-Coupled Neural Networks

1. Front Matter

   Pages i-xxiv

   PDF

2. Biological Models

   • Thomas Lindblad, Jason M. Kinser

   Pages 1-11

3. Programming in Python

   • Thomas Lindblad, Jason M. Kinser

   Pages 13-33

4. NumPy, SciPy and Python Image Library

   • Thomas Lindblad, Jason M. Kinser

   Pages 35-56

5. The PCNN and ICM

   • Thomas Lindblad, Jason M. Kinser

   Pages 57-86

6. Image Analysis

   • Thomas Lindblad, Jason M. Kinser

   Pages 87-105

7. Feedback and Isolation

   • Thomas Lindblad, Jason M. Kinser

   Pages 107-125

8. Recognition and Classification

   • Thomas Lindblad, Jason M. Kinser

   Pages 127-153

9. Texture Recognition

   • Thomas Lindblad, Jason M. Kinser

   Pages 155-170

10. Colour and Multiple Channels

    • Thomas Lindblad, Jason M. Kinser

    Pages 171-185

11. Image Signatures

    • Thomas Lindblad, Jason M. Kinser

    Pages 187-199

12. Logic

    • Thomas Lindblad, Jason M. Kinser

    Pages 201-208

13. Back Matter

    Pages 209-238

    PDF

Image processing algorithms based on the mammalian visual cortex are powerful tools for extraction information and manipulating images. This book reviews the neural theory and translates them into digital models. Applications are given in areas of image recognition, foveation, image fusion and information extraction.
The third edition reflects renewed international interest in pulse image processing with updated sections presenting several newly developed applications. This edition also introduces a suite of Python scripts that assist readers in replicating results presented in the text and to further develop their own applications.

• Applications of Image RecognitionI
• Biomimetic Image Processing
• Digital Models for Image Recognition
• Image Fusion
• Image Processing Algorithms
• Information Extraction
• Mammalian Visual Cortex
• Manipulating Images
• Neural Theory
• Python Scripts

• Dept. Physics, Royal Institute of Technology (KTH), Stockholm, Sweden

  Thomas Lindblad

• , School of Physics and, George Mason University, Fairfax, USA

  Jason M. Kinser

Thomas Lindblad got his Ph.D. at the University of Stockholm in 1974, became associate professor two years later. Dr. Lindblad started his research career in nuclear structure and particle physics with a special interest in detector systems. He soon became the head of the section for Measuring Techniques and Information Processing at the Manne Siegbahn Institute of Physics. He was a frequent visitor to laboratories in Oak Ridge, Berkeley, Orsay, Grenoble and Darmstadt. Later professor Lindblad took a special interest in teaching, started Environmental Physics at the Royal Institute of Technology, Department of Physics, where he also was the director of undergraduate studies for several years. During this time his research interests focused on sensor techniques of different kinds and feature extraction of torrent data flows. A special interest was always the use of neural network hardware with applications to these fields and to diagnostics and environmental monitoring.


Jason Kinser received a D.Sc. in Optics and Electro-Optical Systems in 1994 and an M.S. in Physics in 1987. He joined Alabama A&M in 1994 as an associate research professor as a founding member of the Center for Applied Optical Sciences. He joined George Mason University in 1997 and is now an associate professor in the School of Physics and Computational Sciences at GMU. He has been a visiting scientist at the Royal Institute of Technology (Stockholm) and the Korean University (Seoul). He has also been a visiting scientist at Lawrence-Berkeley National Lab and an external examiner at the University of Mauritius. His research interests started with optical and image information processing including pulse image processing and now extends into processing of data existing in multiple domains.

Policies and ethics