2026-09-19T06:21:11Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1431932022-06-16T03:01:56Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Barbastathis, George
Coykendall, Van R.
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2022-06-15T13:02:35Z
2022-06-15T13:02:35Z
2022-02
2022-02-22T18:32:29.279Z
https://hdl.handle.net/1721.1/143193
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.
M.Eng.
Massachusetts Institute of Technology
In Copyright - Educational Use Permitted
Copyright MIT
http://rightsstatements.org/page/InC-EDU/1.0/
Scene Text Localization and Recognition for Images of Serial Numbers and Odometer Readings
Thesis
application/pdf
Master
Master of Engineering in Electrical Engineering and Computer Science
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="f27b155d-821c-4890-9214-f1a3c24b6bc0">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Title>Scene Text Localization and Recognition for Images of Serial Numbers and Odometer Readings</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2022-02</PublicationDate>
<Authors>
<Author>
<DisplayName>Coykendall, Van R.</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>http://rightsstatements.org/page/InC-EDU/1.0/</License>
<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>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>