Bio-inspired computation and applications in image processing /

Bio-Inspired Computation and Applications in Image Processing summarizes the latest developments in bio-inspired computation in image processing, focusing on nature-inspired algorithms that are linked with deep learning, such as ant colony optimization, particle swarm optimization, and bat and firef...

Descripción completa

Detalles Bibliográficos
Clasificación:Libro Electrónico
Otros Autores: Yang, Xin-She, Papa, Jo�ao Paulo
Formato: Electrónico eBook
Idioma:Inglés
Publicado: London, United Kingdom : Academic Press : Elsevier, 2016.
�20
Temas:
Natural computation.
Image processing > Digital techniques.
Calcul naturel.
Traitement d'images > Techniques num�eriques.
digital imaging.
COMPUTERS > General.
Image processing > Digital techniques
Natural computation
Acceso en línea:Texto completo
Tabla de Contenidos:
  • Cover ; Title page; Copyright page; Contents; List of Contributors; About the editors; Preface; Chapter 1
  • Bio-inspired computation and its applications in image processing: an overview ; 1
  • Introduction; 2
  • Image processing and optimization; 2.1
  • Image segmentation via optimization; 2.2
  • Optimization; 3
  • Some key issues in optimization; 3.1
  • Efficiency of an algorithm; 3.2
  • How to choose algorithms?; 3.3
  • Time and resource constraints; 4
  • Nature-inspired optimization algorithms; 4.1
  • Bio-inspired algorithms based on swarm intelligence; 4.1.1
  • Ant and bee algorithms.
  • 4.1.2
  • Bat algorithm4.1.3
  • Particle swarm optimization; 4.1.4
  • Firefly algorithm; 4.1.5
  • Cuckoo search; 4.1.6
  • Flower pollination algorithm; 4.2
  • Nature-inspired algorithms not based on�swarm�intelligence; 4.2.1
  • Simulated annealing; 4.2.2
  • Genetic algorithms; 4.2.3
  • Differential evolution; 4.2.4
  • Harmony search; 4.3
  • Other algorithms; 5
  • Artificial neural networks and support vector machines; 5.1
  • Artificial neural networks; 5.2
  • Support vector machines; 6
  • Recent trends and applications; 7
  • Conclusions; References.
  • Chapter 2
  • Fine-tuning enhanced probabilistic neural networks using metaheuristic-driven optimization 1
  • Introduction; 2
  • Probabilistic neural network; 2.1
  • Theoretical foundation; 2.2
  • Enhanced probabilistic neural network with local decision circles; 3
  • Methodology and experimental results; 3.1
  • Datasets; 3.2
  • Experimental setup; 3.2.1
  • PNNs versus EPNNs; 3.2.2
  • Evaluating the EPNN and metaheuristic-based EPNNs; 4
  • Conclusions; Acknowledgments; References; Chapter 3
  • Fine-tuning deep belief networks using cuckoo search ; 1
  • Introduction; 2
  • Theoretical background.
  • 2.1
  • Deep belief networks2.1.1
  • Restricted Boltzmann machines; 2.1.2
  • Learning algorithm; 2.2
  • Deep belief nets; 2.3
  • Cuckoo search; 3
  • Methodology; 3.1
  • Datasets; 3.2
  • Harmony search and particle swarm optimization; 4
  • Experiments and results; 4.1
  • Experimental setup; 4.2
  • Experimental results; 5
  • Conclusions; Acknowledgments; References; Chapter 4
  • Improved weighted thresholded histogram equalization algorithm for digital image contrast enhancement using ... ; 1
  • Introduction; 2
  • Literature review; 3
  • Bat algorithm; 4
  • Our proposed method.
  • 4.1
  • Global histogram equalization4.2
  • Development of weighting constraints with respect to the threshold; 4.3
  • Optimizing the weighting constraints using the bat algorithm; 5
  • Experimental results; 6
  • Conclusions; Acknowledgment; References; Chapter 5
  • Ground-glass opacity nodules detection and segmentation using the snake model ; 1
  • Introduction; 2
  • Related works on delineation of GGO lesions; 3
  • Snake model; 3.1
  • Background; 3.2
  • Basic formulation; 3.3
  • Variants of snake models; 4
  • Proposed framework; 4.1
  • Overall framework; 4.2
  • Experimental data; 5
  • Result and discussion.

Ejemplares similares