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
-
Permeating the Blood Brain Barrier and Abrogating the Inflammation in Stroke: Implications for Stroke Therapy
Current Pharmaceutical Design Platelet SERT as a Peripheral Biomarker of Serotonergic Neurotransmission in the Central Nervous System
Current Medicinal Chemistry Metabolic Syndrome Racial Differences in Adolescents
Current Diabetes Reviews Primary Hyperaldosteronism in the Hypertensive Disease
Current Hypertension Reviews Meet Our Editorial Board Member
The Natural Products Journal Cardiac MRI in Autoimmune Diseases: Where Are We Now?
Current Cardiology Reviews Cancer Drug Development Using Glucose Metabolism Radiopharmaceuticals
Current Pharmaceutical Design Development of a Suitable Dissolution Method for the Combined Tablet Formulation of Atorvastatin and Ezetimibe by RP-LC Method
Current Drug Delivery Therapeutic Potential of microRNA Modulation in Pulmonary Arterial Hypertension
Current Vascular Pharmacology Cognitive Impairment and Diabetes
Recent Patents on Endocrine, Metabolic & Immune Drug Discovery (Discontinued) Development of Inhibitors of the Aspartyl Protease Renin for the Treatment of Hypertension
Current Protein & Peptide Science Standardisation of Technique and Volume of Iodinated Contrast Administration During Infrainguinal Angioplasty
Current Pharmaceutical Design Update on Fondaparinux: Role in Management of Thromboembolic and Acute Coronary Events
Cardiovascular & Hematological Agents in Medicinal Chemistry Renal Dysfunction Following Elective Endovascular Aortic Aneurysm Repair
Current Vascular Pharmacology The Role of P-glycoprotein in Cerebral Amyloid Angiopathy; Implications for the Early Pathogenesis of Alzheimers Disease
Current Alzheimer Research Oral Administration of Sustained Release Niacin Inhibits Platelet Aggregation
Current Clinical Pharmacology Recent Patents in Cell Therapy for Amyotrophic Lateral Sclerosis
Recent Patents on Regenerative Medicine The Metabolic Syndrome and Cardiovascular Risk
Current Diabetes Reviews Pharmacological Approach of No-Reflow Phenomenon Related with Percutaneous Coronary Interventions
Cardiovascular & Hematological Agents in Medicinal Chemistry Gastrodia Elata Bl Attenuates Cocaine-Induced Conditioned Place Preference and Convulsion, but not Behavioral Sensitization in Mice: Importance of GABAA Receptors
Current Neuropharmacology