{"id":{"repo_id":"nps","oai_identifier":"oai:calhoun.nps.edu:10945/17317"},"canonical_url":"https://search.dev.ndltd.org/etd/nps/oai:calhoun.nps.edu:10945/17317","repository":{"repo_id":"nps","name":"Naval Postgraduate School","base_url":"https://calhoun.nps.edu/server/oai/request"},"display":{"title":"Improving Identification of Area Targets by Integrated Analysis of Hyperspectral Data and Extracted Texture Features","abstract":"Hyperspectral data were assessed to determine the effect of integrating spectral data and extracted texture features on classification accuracy. Four separate spectral ranges (hundreds of spectral bands total) were used from the VNIR-SWIR portion of the electromagnetic spectrum. Haralick texture features (contrast, entropy, and correlation) were extracted from the average grey level image for each range. A maximum likelihood classifier was trained using a set of ground truth ROIs and applied separately to the spectral data, texture data, and a fused dataset containing both types. Classification accuracy was measured by comparison of results to a separate verification set of ROIs. Analysis indicates that the spectral range used to extract the texture features has a significant effect on the classification accuracy. This result applies to texture-only classifications as well as the classification of integrated spectral and texture data sets. Overall classification improvement for the integrated data sets was near 1per cent. Individual improvement of the Urban class alone showed approximately 9 per cent accuracy increase from spectral-only classification to integrated spectral and texture classification. This research demonstrates the effectiveness of texture features for more accurate analysis of hyperspectral data and the importance of selecting the correct spectral range used to extract these features.","abstract_html":"Hyperspectral data were assessed to determine the effect of integrating spectral data and extracted texture features on classification accuracy. Four separate spectral ranges (hundreds of spectral bands total) were used from the VNIR-SWIR portion of the electromagnetic spectrum. Haralick texture features (contrast, entropy, and correlation) were extracted from the average grey level image for each range. A maximum likelihood classifier was trained using a set of ground truth ROIs and applied separately to the spectral data, texture data, and a fused dataset containing both types. Classification accuracy was measured by comparison of results to a separate verification set of ROIs. Analysis indicates that the spectral range used to extract the texture features has a significant effect on the classification accuracy. This result applies to texture-only classifications as well as the classification of integrated spectral and texture data sets. Overall classification improvement for the integrated data sets was near 1per cent. Individual improvement of the Urban class alone showed approximately 9 per cent accuracy increase from spectral-only classification to integrated spectral and texture classification. This research demonstrates the effectiveness of texture features for more accurate analysis of hyperspectral data and the importance of selecting the correct spectral range used to extract these features.","abstract_has_math":false,"creators":["Bangs, Corey F."],"institution":"Monterey, CA; Naval Postgraduate School","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":"Information Sciences (IS)","school":null,"contributors":[],"advisors":["Kruse, Fred. A."],"committee_chairs":[],"committee_members":[],"year":2012,"date_issued":"2012-09","date_published":"2012-09","updated_at":"2026-07-27T20:26:38Z","subjects":[],"languages":[],"rights":["This publication is a work of the U.S. Government as defined in Title 17, United States Code, Section 101. Copyright protection is not available for this work in the United States."],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/10945/17317","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Kruse, Fred. A."]},{"key":"dc:contributor.department","label":"Department","values":["Information Sciences (IS)"]},{"key":"dc:creator","label":"Author","values":["Bangs, Corey F."]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2012-11-14T00:02:10Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2012-11-14T00:02:10Z"]},{"key":"dc:date.issued","label":"Date","values":["2012-09"]},{"key":"dc:publisher","label":"Institution","values":["Monterey, CA; Naval Postgraduate School"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["This publication is a work of the U.S. Government as defined in Title 17, United States Code, Section 101. Copyright protection is not available for this work in the United States."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10945/17317"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Hyperspectral data were assessed to determine the effect of integrating spectral data and extracted texture features on classification accuracy. Four separate spectral ranges (hundreds of spectral bands total) were used from the VNIR-SWIR portion of the electromagnetic spectrum. Haralick texture features (contrast, entropy, and correlation) were extracted from the average grey level image for each range. A maximum likelihood classifier was trained using a set of ground truth ROIs and applied separately to the spectral data, texture data, and a fused dataset containing both types. Classification accuracy was measured by comparison of results to a separate verification set of ROIs. Analysis indicates that the spectral range used to extract the texture features has a significant effect on the classification accuracy. This result applies to texture-only classifications as well as the classification of integrated spectral and texture data sets. Overall classification improvement for the integrated data sets was near 1per cent. Individual improvement of the Urban class alone showed approximately 9 per cent accuracy increase from spectral-only classification to integrated spectral and texture classification. This research demonstrates the effectiveness of texture features for more accurate analysis of hyperspectral data and the importance of selecting the correct spectral range used to extract these features."]},{"key":"dc:title","label":"Title","values":["Improving Identification of Area Targets by Integrated Analysis of Hyperspectral Data and Extracted Texture Features"]}]}],"canonical_facts":{"dc:contributor.advisor":["Kruse, Fred. A."],"dc:contributor.department":["Information Sciences (IS)"],"dc:creator":["Bangs, Corey F."],"dc:date.accessioned":["2012-11-14T00:02:10Z"],"dc:date.available":["2012-11-14T00:02:10Z"],"dc:date.issued":["2012-09"],"dc:description.abstract":["Hyperspectral data were assessed to determine the effect of integrating spectral data and extracted texture features on classification accuracy. Four separate spectral ranges (hundreds of spectral bands total) were used from the VNIR-SWIR portion of the electromagnetic spectrum. Haralick texture features (contrast, entropy, and correlation) were extracted from the average grey level image for each range. A maximum likelihood classifier was trained using a set of ground truth ROIs and applied separately to the spectral data, texture data, and a fused dataset containing both types. Classification accuracy was measured by comparison of results to a separate verification set of ROIs. Analysis indicates that the spectral range used to extract the texture features has a significant effect on the classification accuracy. This result applies to texture-only classifications as well as the classification of integrated spectral and texture data sets. Overall classification improvement for the integrated data sets was near 1per cent. Individual improvement of the Urban class alone showed approximately 9 per cent accuracy increase from spectral-only classification to integrated spectral and texture classification. This research demonstrates the effectiveness of texture features for more accurate analysis of hyperspectral data and the importance of selecting the correct spectral range used to extract these features."],"dc:identifier.uri":["https://hdl.handle.net/10945/17317"],"dc:publisher":["Monterey, CA; Naval Postgraduate School"],"dc:rights":["This publication is a work of the U.S. Government as defined in Title 17, United States Code, Section 101. Copyright protection is not available for this work in the United States."],"dc:title":["Improving Identification of Area Targets by Integrated Analysis of Hyperspectral Data and Extracted Texture Features"],"dc:type":["Thesis"]},"updated_at":"2026-07-27T20:26:38Z"}