Crystal surface analysis using matrix textural features classified by a Probabilistic Neural Network
Conference
·
OSTI ID:5742463
- Special Technologies Lab., Santa Barbara, CA (USA)
- EG and G Energy Measurements, Inc., Goleta, CA (USA). Santa Barbara Operations
A system is under development in which surface quality of a growing bulk mercuric iodide crystal is monitored by video camera at regular intervals for early detection of growth irregularities. Mercuric iodide single crystals are employed in radiation detectors. A microcomputer system is used for image capture and processing. The digitized image is divided into multiple overlappings subimage and features are extracted from each subimage based on statistical measures of the gray tone distribution, according to the method of Haralick (1). Twenty parameters are derived from each subimage and presented to a Probabilistic Neural Network (PNN) (2) for classification. This number of parameters was found to be optimal for the system. The PNN is a hierarchical, feed-forward network that can be rapidly reconfigured as additional training data become available. Training data is gathered by reviewing digital images of many crystals during their growth cycle and compiling two sets of images, those with and without irregularities. 6 refs., 4 figs.
- Research Organization:
- EG and G Energy Measurements, Inc., Goleta, CA (USA). Santa Barbara Operations
- Sponsoring Organization:
- DOE; USDOE, Washington, DC (USA)
- DOE Contract Number:
- AC08-88NV10617
- OSTI ID:
- 5742463
- Report Number(s):
- EGG-10617-3004; CONF-9107115--3; ON: DE91014120
- Country of Publication:
- United States
- Language:
- English
Similar Records
Parametrization of textural patterns in {sup 123}I-ioflupane imaging for the automatic detection of Parkinsonism
Parametrization of textural patterns in {sup 123}I-ioflupane imaging for the automatic detection of Parkinsonism
Damage identification with probabilistic neural networks
Journal Article
·
Tue Jan 14 23:00:00 EST 2014
· Medical Physics
·
OSTI ID:22251245
Parametrization of textural patterns in {sup 123}I-ioflupane imaging for the automatic detection of Parkinsonism
Journal Article
·
Tue Jan 14 23:00:00 EST 2014
· Medical Physics
·
OSTI ID:22251738
Damage identification with probabilistic neural networks
Conference
·
Thu Nov 30 23:00:00 EST 1995
·
OSTI ID:150953
Related Subjects
36 MATERIALS SCIENCE
360601* -- Other Materials-- Preparation & Manufacture
360602 -- Other Materials-- Structure & Phase Studies
440100 -- Radiation Instrumentation
46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND TECHNOLOGY
CAMERAS
CRYSTAL GROWTH
HALIDES
HALOGEN COMPOUNDS
IMAGE PROCESSING
IMAGES
IODIDES
IODINE COMPOUNDS
MATHEMATICS
MATRICES
MEASURING INSTRUMENTS
MERCURY COMPOUNDS
MERCURY HALIDES
MERCURY IODIDES
MONITORING
NEURAL NETWORKS
PATTERN RECOGNITION
PROCESSING
RADIATION DETECTORS
STATISTICS
360601* -- Other Materials-- Preparation & Manufacture
360602 -- Other Materials-- Structure & Phase Studies
440100 -- Radiation Instrumentation
46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND TECHNOLOGY
CAMERAS
CRYSTAL GROWTH
HALIDES
HALOGEN COMPOUNDS
IMAGE PROCESSING
IMAGES
IODIDES
IODINE COMPOUNDS
MATHEMATICS
MATRICES
MEASURING INSTRUMENTS
MERCURY COMPOUNDS
MERCURY HALIDES
MERCURY IODIDES
MONITORING
NEURAL NETWORKS
PATTERN RECOGNITION
PROCESSING
RADIATION DETECTORS
STATISTICS