A joint compression-discrimination neural transformation applied to target detection

Autor: Nasser M. Nasrabadi, Alex Chan, Sandor Z. Der
Rok vydání: 2005
Předmět:
Computer science
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
Information Storage and Retrieval
Machine learning
computer.software_genre
Pattern Recognition
Automated
Generalized Hebbian Algorithm
Artificial Intelligence
Image Interpretation
Computer-Assisted
Cluster Analysis
Computer Simulation
Electrical and Electronic Engineering
Representation (mathematics)
Principal Component Analysis
Models
Statistical
Radar
Contextual image classification
business.industry
Dimensionality reduction
Pattern recognition
General Medicine
Image Enhancement
Backpropagation
Computer Science Applications
Human-Computer Interaction
ComputingMethodologies_PATTERNRECOGNITION
Transformation (function)
Control and Systems Engineering
Computer Science::Computer Vision and Pattern Recognition
Subtraction Technique
Principal component analysis
Artificial intelligence
Neural Networks
Computer
business
computer
Software
Algorithms
Information Systems
Data compression
Zdroj: IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society. 35(4)
ISSN: 1083-4419
Popis: Many image recognition algorithms based on data-learning perform dimensionality reduction before the actual learning and classification because the high dimensionality of raw imagery would require enormous training sets to achieve satisfactory performance. A potential problem with this approach is that most dimensionality reduction techniques, such as principal component analysis (PCA), seek to maximize the representation of data variation into a small number of PCA components, without considering interclass discriminability. This paper presents a neural-network-based transformation that simultaneously seeks to provide dimensionality reduction and a high degree of discriminability by combining together the learning mechanism of a neural-network-based PCA and a backpropagation learning algorithm. The joint discrimination-compression algorithm is applied to infrared imagery to detect military vehicles.
Databáze: OpenAIRE
Externí odkaz: