Show simple item record

dc.contributor.advisorAndriamanalimanana, Bruno R.; Thesis Advisor
dc.contributor.advisorNovillo, Jorge; Thesis Committee
dc.contributor.advisorSpetka, Scott; Thesis Committee
dc.contributor.authorGoda, Piyush Jain
dc.date.accessioned2021-08-05T19:13:16Z
dc.date.available2021-08-05T19:13:16Z
dc.date.issued2020-12
dc.identifier.urihttp://hdl.handle.net/20.500.12648/2036
dc.description.abstractRecently, a variety of real-world applications have triggered a huge demand for techniques that can extract textual information from images and videos. Therefore, image text detection and recognition have become active research topics in computer vision. The current trend in object detection and localization is to learn predictions with high capacity deep neural networks trained on a very large amount of annotated data and using a high amount of processing power. In this project, I have built an approach for text detection using the object detection technique. Our approach is to deal with the text as objects. We use an object detection method, YOLO (You Only Look Once), to detect the text in the images. We frame object detection as a regression problem to spatially separated bounding boxes and associated class probabilities. YOLO, a single neural network, that predicts bounding boxes and class probabilities directly from full images in one evaluation. Since the whole detection pipeline is a single network, it can be optimized end-to-end directly on detection performance. The MobileNet pre-trained deep learning model architecture was used and modified in different ways to find the best performing model. The goal is to achieve high accuracy in text spotting. Experiments on standard datasets ICDAR 2015 demonstrate that the proposed algorithm significantly outperforms methods in terms of both accuracy and efficiency.en_US
dc.language.isoen_USen_US
dc.subjectimage text detection and recognitionen_US
dc.subjectcomputer visionen_US
dc.subjectConvolution Neural Network (CNN)en_US
dc.subjectObject Detectionen_US
dc.subjectYOLO (You Only Look Once)en_US
dc.subjectSingle Shot Detector (SSD)en_US
dc.subjectMobileNeten_US
dc.subjectPythonen_US
dc.titleText Detection from an Imageen_US
dc.typeThesisen_US
dc.description.versionNAen_US
refterms.dateFOA2021-08-05T19:13:17Z
dc.description.institutionSUNY Polytechnic Instituteen_US
dc.description.departmentCollege of Engineeringen_US
dc.description.degreelevelMSen_US


Files in this item

Thumbnail
Name:
Goda_P_Project_report.pdf
Size:
1.925Mb
Format:
PDF
Description:
Final Thesis Submission
Thumbnail
Name:
Goda_P_signed_Declaration.pdf
Size:
84.92Kb
Format:
PDF
Description:
Declaration
Thumbnail
Name:
Goda_waiver.pdf
Size:
335.0Kb
Format:
PDF
Description:
Copyright Waiver
Thumbnail
Name:
P_Goda_signed_Advisor_sheet.pdf
Size:
121.3Kb
Format:
PDF

This item appears in the following Collection(s)

  • SUNY Polytechnic Institute College of Engineering
    This collection contains master's theses, capstone projects, and other student and faculty work from programs within the Department of Engineering, including computer science and network security.

Show simple item record