Classification of thermally condition monitored components using statistical and neural network techniques

Proceedings of SPIE - The International Society for Optical Engineering

Volumn 3164, Issue , 1997, Pages 573-581

  Moja, Nathan T ^a   Willis, Andrew J ^a  

^a Eskom Technology Res and Invest   (United States)

Author keywords

Feature extraction; Image enhancement; Neural network classifier; Principal component analysis; Statistical classifier; Thermal pattern

Indexed keywords

CLUTTER (INFORMATION THEORY); FEATURE EXTRACTION; NEURAL NETWORKS; PRINCIPAL COMPONENT ANALYSIS; STATISTICAL METHODS; THERMOANALYSIS; VECTOR QUANTIZATION;

THERMAL IMAGE DATABASES;

IMAGE ENHANCEMENT;

EID: 0031289521     PISSN: 0277786X     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1117/12.279582     Document Type: Conference Paper

References (11)

1. The use of infrared thermography in evaluating substation transformers
2. An optical Fourier/electronic neurocomputer automated inspection system
3. Algebraic feature extraction of image for recognition
4. The use of singular systems and other inversion methods
5. Small sample size effects in statistical pattern recognition: Recommendations for practitioners