Abstract
Introduction: Segmentation and recognition of text from the scene image are a challenging task due to blurred, low-resolution and small sized image.
Materials and Methods: Innovative methods have been proposed to address this problem and to recognize the text from the natural scene image. The acquired image is pre-processed by the YUV channel conversion technique and the Y channel image is converted to a gray scale image. Connected Component Based Text Segmentation Algorithm (CCBTSA) and MSER methods are used for segmentation and recognition of text using Optical Character Recognition (OCR). GLCM and FOS features are extracted from the segmented region. The Template matching algorithm is used to extract the text character from the bounding box of the segmented image.
Results and Conclusion: Trained SVM classifier is used to classify the image containing text and non-text region. Performances are analyzed based on the recall rate, precision, accuracy, and Fmeasure. From the experimental results, the accuracy of the proposed classifier was obtained as 95%.
Keywords: Text segmentation, connected component, segmentation algorithm, maximally stable, optical character recognition, template matching.
Graphical Abstract
Current Signal Transduction Therapy
Title:Automatic Text Segmentation and Recognition in Natural Scene Images Using Msocr
Volume: 15 Issue: 3
Author(s): S.R. Surem Samuel*, Christopher C. Seldev and S. Jinny Vinila
Affiliation:
- Department of ECE, CSI Institute of Technology, Thovalai,India
Keywords: Text segmentation, connected component, segmentation algorithm, maximally stable, optical character recognition, template matching.
Abstract:
Introduction: Segmentation and recognition of text from the scene image are a challenging task due to blurred, low-resolution and small sized image.
Materials and Methods: Innovative methods have been proposed to address this problem and to recognize the text from the natural scene image. The acquired image is pre-processed by the YUV channel conversion technique and the Y channel image is converted to a gray scale image. Connected Component Based Text Segmentation Algorithm (CCBTSA) and MSER methods are used for segmentation and recognition of text using Optical Character Recognition (OCR). GLCM and FOS features are extracted from the segmented region. The Template matching algorithm is used to extract the text character from the bounding box of the segmented image.
Results and Conclusion: Trained SVM classifier is used to classify the image containing text and non-text region. Performances are analyzed based on the recall rate, precision, accuracy, and Fmeasure. From the experimental results, the accuracy of the proposed classifier was obtained as 95%.
Export Options
About this article
Cite this article as:
Samuel Surem S.R. *, Seldev C. Christopher and Vinila Jinny S. , Automatic Text Segmentation and Recognition in Natural Scene Images Using Msocr, Current Signal Transduction Therapy 2020; 15 (3) . https://dx.doi.org/10.2174/1574362414666190725105748
DOI https://dx.doi.org/10.2174/1574362414666190725105748 |
Print ISSN 1574-3624 |
Publisher Name Bentham Science Publisher |
Online ISSN 2212-389X |
- Author Guidelines
- Graphical Abstracts
- Fabricating and Stating False Information
- Research Misconduct
- Post Publication Discussions and Corrections
- Publishing Ethics and Rectitude
- Increase Visibility of Your Article
- Archiving Policies
- Peer Review Workflow
- Order Your Article Before Print
- Promote Your Article
- Manuscript Transfer Facility
- Editorial Policies
- Allegations from Whistleblowers
- Announcements
Related Articles
-
Skeletal Muscle Derived Stem Cells for Myocardial Repair
Recent Patents on Cardiovascular Drug Discovery Mapping of the Active Site of Proteases in the 1960s and Rational Design of Inhibitors/Drugs in the 1990s
Current Protein & Peptide Science Electroporation: An Avenue for Transdermal Drug Delivery
Current Drug Delivery Pro-Inflammatory Gene Variants in Myocardial Infarction and Longevity: Implications for Pharmacogenomics
Current Pharmaceutical Design Novel Coronavirus Disease 2019 (COVID-19) Current Update: Perspective on Epidemiology, Diagnosis, Drug Targets and Vaccines
Coronaviruses Heart Failure Pharmacotherapy: Differences Between Adult and Paediatric Patients
Current Medicinal Chemistry Is Combination Therapy of Atosiban and Nifedipine More Effective in Preterm Labor than Each Drug Alone? A Prospective Study
Current Women`s Health Reviews Auto-Antibodies As Possible Markers and Mediators of Ischemic, Dilated, and Rhythmic Cardiopathies
Current Drug Targets Meet Our Editorial Board Member
Current Vascular Pharmacology Drug-Induced QTc Interval Prolongation: A Multicenter Study to Detect Drugs and Clinical Factors Involved in Every Day Practice
Current Drug Safety Sympathetic Overactivity in Patients with Chronic Renal Failure - The Culprit of Increased Cardiovascular Mortality?
Current Hypertension Reviews Effects of Polyphenolic Derivatives on Heme Oxygenase-System in Metabolic Dysfunctions
Current Medicinal Chemistry Patent Selections
Recent Patents on CNS Drug Discovery (Discontinued) ROCK Inhibitors as Emerging Therapeutic Candidates for Sarcomas
Current Cancer Drug Targets Neurovascular Mechanisms of Hypertension in Pregnancy
Current Neurovascular Research Clinical Determination of the Severity of Metabolic Syndrome: Preheparin Lipoprotein Lipase Mass as a New Marker of Metabolic Syndrome
Current Medicinal Chemistry - Cardiovascular & Hematological Agents Inhibitors of Cytosolic Phospholipase A2α as Potential Anti-Inflammatory Drugs
Anti-Inflammatory & Anti-Allergy Agents in Medicinal Chemistry Coagulation Factor XIIIA (F13A1): Novel Perspectives in Treatment and Pharmacogenetics
Current Pharmaceutical Design Cognitive Impairment, Neuroimaging, and Alzheimer Neuropathology in Mouse Models of Down Syndrome
Current Alzheimer Research Discovery-Based Strategies for Studying Platelet Function
Mini-Reviews in Medicinal Chemistry