{"id":{"repo_id":"vt","oai_identifier":"oai:vtechworks.lib.vt.edu:10919/9988"},"canonical_url":"https://search.dev.ndltd.org/etd/vt/oai:vtechworks.lib.vt.edu:10919/9988","repository":{"repo_id":"vt","name":"Virginia Tech","base_url":"https://vtechworks.lib.vt.edu/oai/request"},"display":{"title":"Experiments in Image Segmentation for Automatic US License Plate Recognition","abstract":"License plate recognition/identification (LPR/I) applies image processing and character recognition technology to identify vehicles by automatically reading their license plates. In the United States, however, each state has its own standard-issue plates, plus several optional styles, which are referred to as special license plates or varieties. There is a clear absence of standardization and multi-colored, complex backgrounds are becoming more frequent in license plates. Commercially available optical character recognition (OCR) systems generally fail when confronted with textured or poorly contrasted backgrounds, therefore creating the need for proper image segmentation prior to classification. The image segmentation problem in LPR is examined in two stages: license plate region detection and license plate character extraction from background. Three different approaches for license plate detection in a scene are presented: region distance from eigenspace, border location by edge detection and the Hough transform, and text detection by spectral analysis. The experiments for character segmentation involve the RGB, HSV/HSI and 1976 CIE L*a*b* color spaces as well as their Karhunen-Loéve transforms. The segmentation techniques applied include multivariate hierarchical agglomerative clustering and minimum-variance color quantization. The trade-off between accuracy and computational expense is used to select a final reliable algorithm for license plate detection and character segmentation. The spectral analysis approach together with the K-L L*a*b* transformed color quantization are found experimentally as the best alternatives for the two identified image segmentation stages for US license plate recognition.","abstract_html":"License plate recognition/identification (LPR/I) applies image processing and character recognition technology to identify vehicles by automatically reading their license plates. In the United States, however, each state has its own standard-issue plates, plus several optional styles, which are referred to as special license plates or varieties. There is a clear absence of standardization and multi-colored, complex backgrounds are becoming more frequent in license plates. Commercially available optical character recognition (OCR) systems generally fail when confronted with textured or poorly contrasted backgrounds, therefore creating the need for proper image segmentation prior to classification. The image segmentation problem in LPR is examined in two stages: license plate region detection and license plate character extraction from background. Three different approaches for license plate detection in a scene are presented: region distance from eigenspace, border location by edge detection and the Hough transform, and text detection by spectral analysis. The experiments for character segmentation involve the RGB, HSV/HSI and 1976 CIE L*a*b* color spaces as well as their Karhunen-Loéve transforms. The segmentation techniques applied include multivariate hierarchical agglomerative clustering and minimum-variance color quantization. The trade-off between accuracy and computational expense is used to select a final reliable algorithm for license plate detection and character segmentation. The spectral analysis approach together with the K-L L*a*b* transformed color quantization are found experimentally as the best alternatives for the two identified image segmentation stages for US license plate recognition.","abstract_has_math":false,"creators":["Diaz Acosta, Beatriz"],"institution":"Virginia Tech","degree_name":"Master of Science","degree_level":"masters","degree_discipline":"Computer Science","degree_department":"Computer Science","school":null,"contributors":[],"advisors":[],"committee_chairs":["Ehrich, Roger W."],"committee_members":["Ribbens, Calvin J.","Wyatt, Christopher L.","Abbott, A. Lynn"],"year":2004,"date_issued":"2004-06-21","date_published":"2004-06-21","updated_at":"2026-07-22T22:19:42Z","subjects":["Data Cluster Analysis","Hough Transform","Spectral Analysis","Color Image Segmentation","License Plate Recognition","Minimum-Variance Quantization"],"languages":[],"rights":["In Copyright"],"rights_urls":["http://rightsstatements.org/vocab/InC/1.0/"],"identifier_entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["etd-07022004-132444"],"render_values":[{"text":"etd-07022004-132444","href":null,"code":true}]}]},"links":{"outbound_url":"http://hdl.handle.net/10919/9988","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.committeechair","label":"Committee Chair","values":["Ehrich, Roger W."]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Ribbens, Calvin J.","Wyatt, Christopher L.","Abbott, A. Lynn"]},{"key":"dc:contributor.department","label":"Department","values":["Computer Science"]},{"key":"dc:creator","label":"Author","values":["Diaz Acosta, Beatriz"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2011-08-06T16:02:13Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2011-08-06T16:02:13Z","2004-07-09"]},{"key":"dc:date.issued","label":"Date","values":["2004-06-21"]},{"key":"dc:publisher","label":"Institution","values":["Virginia Tech"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["masters"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["Virginia Polytechnic Institute and State University"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Data Cluster Analysis","Hough Transform","Spectral Analysis","Color Image Segmentation","License Plate Recognition","Minimum-Variance Quantization"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["In Copyright"]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://rightsstatements.org/vocab/InC/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["etd-07022004-132444"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://hdl.handle.net/10919/9988"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["License plate recognition/identification (LPR/I) applies image processing and character recognition technology to identify vehicles by automatically reading their license plates. In the United States, however, each state has its own standard-issue plates, plus several optional styles, which are referred to as special license plates or varieties. There is a clear absence of standardization and multi-colored, complex backgrounds are becoming more frequent in license plates. Commercially available optical character recognition (OCR) systems generally fail when confronted with textured or poorly contrasted backgrounds, therefore creating the need for proper image segmentation prior to classification. The image segmentation problem in LPR is examined in two stages: license plate region detection and license plate character extraction from background. Three different approaches for license plate detection in a scene are presented: region distance from eigenspace, border location by edge detection and the Hough transform, and text detection by spectral analysis. The experiments for character segmentation involve the RGB, HSV/HSI and 1976 CIE L*a*b* color spaces as well as their Karhunen-Loéve transforms. The segmentation techniques applied include multivariate hierarchical agglomerative clustering and minimum-variance color quantization. The trade-off between accuracy and computational expense is used to select a final reliable algorithm for license plate detection and character segmentation. The spectral analysis approach together with the K-L L*a*b* transformed color quantization are found experimentally as the best alternatives for the two identified image segmentation stages for US license plate recognition."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Master of Science"]},{"key":"dc:format.medium","label":"Dc Format Medium","values":["ETD"]},{"key":"dc:title","label":"Title","values":["Experiments in Image Segmentation for Automatic US License Plate Recognition"]}]}],"canonical_facts":{"dc:contributor.committeechair":["Ehrich, Roger W."],"dc:contributor.committeemember":["Ribbens, Calvin J.","Wyatt, Christopher L.","Abbott, A. Lynn"],"dc:contributor.department":["Computer Science"],"dc:creator":["Diaz Acosta, Beatriz"],"dc:date.accessioned":["2011-08-06T16:02:13Z"],"dc:date.available":["2011-08-06T16:02:13Z","2004-07-09"],"dc:date.issued":["2004-06-21"],"dc:description.abstract":["License plate recognition/identification (LPR/I) applies image processing and character recognition technology to identify vehicles by automatically reading their license plates. In the United States, however, each state has its own standard-issue plates, plus several optional styles, which are referred to as special license plates or varieties. There is a clear absence of standardization and multi-colored, complex backgrounds are becoming more frequent in license plates. Commercially available optical character recognition (OCR) systems generally fail when confronted with textured or poorly contrasted backgrounds, therefore creating the need for proper image segmentation prior to classification. The image segmentation problem in LPR is examined in two stages: license plate region detection and license plate character extraction from background. Three different approaches for license plate detection in a scene are presented: region distance from eigenspace, border location by edge detection and the Hough transform, and text detection by spectral analysis. The experiments for character segmentation involve the RGB, HSV/HSI and 1976 CIE L*a*b* color spaces as well as their Karhunen-Loéve transforms. The segmentation techniques applied include multivariate hierarchical agglomerative clustering and minimum-variance color quantization. The trade-off between accuracy and computational expense is used to select a final reliable algorithm for license plate detection and character segmentation. The spectral analysis approach together with the K-L L*a*b* transformed color quantization are found experimentally as the best alternatives for the two identified image segmentation stages for US license plate recognition."],"dc:description.degree":["Master of Science"],"dc:format.medium":["ETD"],"dc:identifier.other":["etd-07022004-132444"],"dc:identifier.uri":["http://hdl.handle.net/10919/9988"],"dc:publisher":["Virginia Tech"],"dc:rights":["In Copyright"],"dc:rights.uri":["http://rightsstatements.org/vocab/InC/1.0/"],"dc:subject":["Data Cluster Analysis","Hough Transform","Spectral Analysis","Color Image Segmentation","License Plate Recognition","Minimum-Variance Quantization"],"dc:title":["Experiments in Image Segmentation for Automatic US License Plate Recognition"],"dc:type":["Thesis"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["masters"],"thesis:degree_name":["Master of Science"],"thesis:institution_name":["Virginia Polytechnic Institute and State University"]},"updated_at":"2026-07-22T22:19:42Z"}