Date of Award
Master of Science
Department of Electrical and Computer Engineering
Jeffrey D. Clark, PhD.
The ability to accurately and quickly locate an individual, or a dismount, is useful in a variety of situations and environments. A dismount's characteristics such as their gender, height, weight, build, and ethnicity could be used as discriminating factors. Hyperspectral imaging (HSI) is widely used in efforts to identify materials based on their spectral signatures. More specifically, HSI has been used for skin and clothing classification and detection. The ability to detect textiles (clothing) provides a discriminating factor that can aid in a more comprehensive detection of dismounts. This thesis demonstrates the application of several feature selection methods (i.e., support vector machines with recursive feature reduction, fast correlation based filter) in highly dimensional data collected from a spectroradiometer. The classification of the data is accomplished with the selected features and artificial neural networks. A model for uniquely identifying (fingerprinting) textiles are designed, where color and composition are determined in order to fingerprint a specific textile. An artificial neural network is created based on the knowledge of the textile's color and composition, providing a uniquely identifying fingerprinting of a textile. Results show 100% accuracy for color and composition classification, and 98% accuracy for the overall textile fingerprinting process.
DTIC Accession Number
Yeom, Jennifer S., "Textile Fingerprinting for Dismount Analysis in the Visible, Near, and Shortwave Infrared Domain" (2014). Theses and Dissertations. 637.