Doctoral Dissertations

Kapil Gupta

Abstract

"Data fusion is generally practiced to enhance decision or inference making capability. Sensor and information source data may often be corrupted by noise or other factors. Data fusion can be used to improve sensor and/or information source data quality and reliability and improve detection accuracy. There are several types of data fusion, including raw data level, feature level, and decision level.

This work presents the investigation and development of image and signal processing, computational intelligence, fuzzy logic, and statistical techniques for different types of data fusion for a varied range of applications. Raw data and decision level fusion approaches are investigated for detection and quantification of corrosion for structural health monitoring of aging aircrafts. Also, feature level fusion techniques are explored for detection of malignant melanoma from dermoscopy images of skin lesions, and the detection of abnormal growth in vertebrae of the spine in x-ray images"--Abstract, page iv.

Advisor(s)

Stanley, R. Joe

Committee Member(s)

Chandrashekhara, K.
Stoecker, William V.
Moss, Randy Hays, 1953-
Zoughi, R.

Department(s)

Electrical and Computer Engineering

Degree Name

Ph. D. in Electrical Engineering

Publisher

University of Missouri--Rolla

Publication Date

Fall 2007

Journal article titles appearing in thesis/dissertation

  • Fusion of microwave and eddy current data for a multi-modal approach in evaluating corrosion under paint and in lap-joints
  • Fusion of multimodal NDE data for improved corrosion detection
  • Data fusion based approach for evaluation of material loss in corroded aluminum panels
  • Detection of asymmetric blotches (asymmetric structureless areas) in dermoscopy images of malignant melanoma using relative color
  • Fuzzy logic techniques in blotch feature evaluation for melanoma discrimination from dermoscopy images
  • Detection of globules in dermoscopy images of malignant melanoma: absolute vs. relative color
  • Fuzzy-based histogram analysis technique for skin lesion discrimination in dermatology dermoscopy images
  • Size-invariant descriptors for detecting regions of abnormal growth in cervical vertebra

Pagination

xv, 217 pages

Note about bibliography

Includes bibliographical references.

Rights

© 2007 Kapil Gupta, All rights reserved.

Document Type

Dissertation - Open Access

File Type

text

Language

English

Subject Headings

Airplanes -- CorrosionEddy current testingFuzzy logicImage analysis -- TechniqueMelanoma -- Diagnosis -- Computer programsMultisensor data fusionNondestructive testingStructural analysis (Engineering)

Thesis Number

T 9888

Print OCLC #

793105123

Electronic OCLC #

905721241

Download

Share

 
COinS