Analysis and design of optimal deep neural network model for image recognition using hybrid cuckoo search with self-adaptive particle swarm intelligence

Image recognition involves identifying objects in digital photos via computer algorithms and machine learning. Integrating cooperative behaviours and adaptive dynamics, bio-inspired swarm intelligence optimizes multiple algorithms for efficient solutions to complex challenges. CSO and SaPSO is combi...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Signal, image and video processing Jg. 18; H. 10; S. 6987 - 6995
Hauptverfasser: Shelar, Alankar, Kulkarni, Raj
Format: Journal Article
Sprache:Englisch
Veröffentlicht: London Springer London 01.09.2024
Springer Nature B.V
Schlagworte:
Accuracy
Algorithms
Artificial neural networks
Biodegradable materials
Classification
Computer Imaging
Computer Science
Data collection
Datasets
Digital computers
Generative adversarial networks
Image Processing and Computer Vision
Machine learning
Multimedia Information Systems
Neural networks
Optimization
Original Paper
Pattern Recognition and Graphics
Signal,Image and Speech Processing
Swarm intelligence
Vision
Deep neural network
Image recognition
Self-adaptive particle swarm intelligence
Hybrid cuckoo search
Bio-inspired swarm intelligence
ISSN:1863-1703, 1863-1711
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Image recognition involves identifying objects in digital photos via computer algorithms and machine learning. Integrating cooperative behaviours and adaptive dynamics, bio-inspired swarm intelligence optimizes multiple algorithms for efficient solutions to complex challenges. CSO and SaPSO is combined in this framework for enhanced optimization efficiency, promising faster convergence and better solutions. Employing Deep Convolution Generative Adversarial Networks (DC-GAN) for classification, the study achieves an outstanding 99.5% accuracy using Python. Through feature extraction, accuracy reaches 99%, indicating precise classification with minimal error. Key terms: DNN, Image Recognition, Bio-Inspired Swarm Intelligence, Hybrid Cuckoo Search, Self-Adaptive Particle Swarm Intelligence.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1863-1703
1863-1711
DOI:10.1007/s11760-024-03368-x