{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/143193"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/143193","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Scene Text Localization and Recognition for Images of Serial Numbers and Odometer Readings","abstract":"This thesis investigates deep learning models and methods to create a full scene text extraction system. The system is composed of two main parts, a localization network and a recognition network, with the recognition network being the main focus. The localization network is a segmentation network that localizes the region in an image containing text. Once this region is identified the recognition network predicts the text within the image. In addition to investigating these models, we look at data processing, data generation, and model prediction processing techniques to improve the system’s robustness and make the learning processes easier.","abstract_html":"This thesis investigates deep learning models and methods to create a full scene text extraction system. The system is composed of two main parts, a localization network and a recognition network, with the recognition network being the main focus. The localization network is a segmentation network that localizes the region in an image containing text. Once this region is identified the recognition network predicts the text within the image. In addition to investigating these models, we look at data processing, data generation, and model prediction processing techniques to improve the system’s robustness and make the learning processes easier.","abstract_has_math":false,"creators":["Coykendall, Van R."],"institution":"Massachusetts Institute of Technology","degree_name":"Master","degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science","school":null,"contributors":[],"advisors":["Barbastathis, George"],"committee_chairs":[],"committee_members":[],"year":2022,"date_issued":"2022-02","date_published":"2022-02","updated_at":"2026-07-22T22:22:26Z","subjects":[],"languages":[],"rights":["In Copyright - Educational Use Permitted","Copyright MIT"],"rights_urls":["http://rightsstatements.org/page/InC-EDU/1.0/"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1721.1/143193","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Barbastathis, George"]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"]},{"key":"dc:creator","label":"Author","values":["Coykendall, Van R."]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2022-06-15T13:02:35Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2022-06-15T13:02:35Z"]},{"key":"dc:date.issued","label":"Date","values":["2022-02"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master","Master of Engineering in Electrical Engineering and Computer Science"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["In Copyright - Educational Use Permitted","Copyright MIT"]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://rightsstatements.org/page/InC-EDU/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1721.1/143193"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["This thesis investigates deep learning models and methods to create a full scene text extraction system. The system is composed of two main parts, a localization network and a recognition network, with the recognition network being the main focus. The localization network is a segmentation network that localizes the region in an image containing text. Once this region is identified the recognition network predicts the text within the image. In addition to investigating these models, we look at data processing, data generation, and model prediction processing techniques to improve the system’s robustness and make the learning processes easier."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["M.Eng."]},{"key":"dc:title","label":"Title","values":["Scene Text Localization and Recognition for Images of Serial Numbers and Odometer Readings"]}]}],"canonical_facts":{"dc:contributor.advisor":["Barbastathis, George"],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"],"dc:creator":["Coykendall, Van R."],"dc:date.accessioned":["2022-06-15T13:02:35Z"],"dc:date.available":["2022-06-15T13:02:35Z"],"dc:date.issued":["2022-02"],"dc:description.abstract":["This thesis investigates deep learning models and methods to create a full scene text extraction system. The system is composed of two main parts, a localization network and a recognition network, with the recognition network being the main focus. The localization network is a segmentation network that localizes the region in an image containing text. Once this region is identified the recognition network predicts the text within the image. In addition to investigating these models, we look at data processing, data generation, and model prediction processing techniques to improve the system’s robustness and make the learning processes easier."],"dc:description.degree":["M.Eng."],"dc:identifier.uri":["https://hdl.handle.net/1721.1/143193"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["In Copyright - Educational Use Permitted","Copyright MIT"],"dc:rights.uri":["http://rightsstatements.org/page/InC-EDU/1.0/"],"dc:title":["Scene Text Localization and Recognition for Images of Serial Numbers and Odometer Readings"],"dc:type":["Thesis"],"thesis:degree_name":["Master","Master of Engineering in Electrical Engineering and Computer Science"]},"updated_at":"2026-07-22T22:22:26Z"}