Melola Discovery

← Melola Discovery

Open access Journal SINTA 1

Customized mask region based convolutional neural networks for un-uniformed shape text detection and text recognition

International Journal of Electrical and Computer Engineering (IJECE) · Vol. 13 No. 1 (2023)

DOI
10.11591/ijece.v13i1.pp413-424
ISSN
2722-2578, 2088-8708
Published
2023-02-01
Publisher
Institute of Advanced Engineering and Science
License
creativecommons.org/licenses/by-sa/4.0

Abstract

In image scene, text contains high-level of important information that helps to analyze and consider the particular environment. In this paper, we adapt image mask and original identification of the mask region based convolutional neural networks (R-CNN) to allow recognition at 3 levels such as sequence, holistic and pixel-level semantics. Particularly, pixel and holistic level semantics can be utilized to recognize the texts and define the text shapes, respectively. Precisely, in mask and detection, we segment and recognize both character and word instances. Furthermore, we implement text detection through the outcome of instance segmentation on 2-D feature-space. Also, to tackle and identify the text issues of smaller and blurry texts, we consider text recognition by attention-based of optical character recognition (OCR) model with the mask R-CNN at sequential level. The OCR module is used to estimate character sequence through feature maps of the word instances in sequence to sequence. Finally, we proposed a fine-grained learning technique that trains a more accurate and robust model by learning models from the annotated datasets at the word level. Our proposed approach is evaluated on popular benchmark dataset ICDAR 2013 and ICDAR 2015.

Collaboration network of the authors

24 authors · 71 co-authorship links · 25 across different organisations

Hover or tap a name to highlight its co-authors. Double-click to open the author's page.

  • Christ University
  • Dayananda Sagar University
  • Dayananda Sagar Academy of Technology and Management
  • Dayananda Sagar College of Engineering
  • Amrita Vishwa Vidyapeetham
  • Jawaharlal Nehru New College of Engineering
  • Affiliation unknown
  • Different organisations
  • Same organisation
  • Affiliation unknown
  • Thicker line = more joint articles · bigger circle = more articles
Show as table
Co-authorOrganisationJoint articles
Santosh Kumar JankattiDayananda Sagar University9
Niranjana Shravanabelagola JinachandraChrist University4
Niranjana Shravanabelagola JinachandraChrist University2
Manjunath Ramanna LamaniAffiliation unknown2
Vinai George BijuAffiliation unknown2
M. Shahina ParveenDayananda Sagar University2
Harish H. KenchannavarDayananda Sagar College of Engineering2
Danthuluri SudhaDayananda Sagar University2
Srihari Sharma K NDayananda Sagar University2
B MeenakshiAffiliation unknown2
Raveendra Kumar Tavarekere HombegowdaAffiliation unknown2
Meenakshi MeenakshiDayananda Sagar University1
Ravikumar Hodikehosalli ChennegowdaAffiliation unknown1
Bellam Vijaya LakshmiChrist University1
Rishita BhelwaChrist University1
Namitha Thattarassery NanappanChrist University1
Vinith RejathalalAmrita Vishwa Vidyapeetham1
Deepak M. DevendrappaAffiliation unknown1
Deepak N. AnanthAffiliation unknown1
Arun Kumar P.Jawaharlal Nehru New College of Engineering1

Affiliations come from OpenAlex; journal OAI-PMH metadata carries none. Authors without an OpenAlex ID are matched by name, which can merge or split people.

This record comes from Crossref (what the publisher deposited), because the journal's own OAI-PMH endpoint could not be harvested.

Metadata source: Crossref API (cadangan, berdasarkan ISSN) https://api.crossref.org/journals/2088-8708/works, first harvested 27 Oct 2026, last seen 15 Nov 2026.
Metadata as oai_dc, converted from Crossref
<oai_dc:dc xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/"><dc:title>Customized mask region based convolutional neural networks for un-uniformed shape text detection and text recognition</dc:title><dc:creator>Channegowda, Ravikumar Hodikehosahally</dc:creator><dc:creator>Karthik, Palani</dc:creator><dc:creator>Srinivasaiah, Raghavendra</dc:creator><dc:creator>Shivaraj, Mahadev</dc:creator><dc:description>&lt;jats:p&gt;&amp;lt;p&amp;gt;&amp;lt;span lang="EN-US"&amp;gt;In image scene, text contains high-level of important information that helps to analyze and consider the particular environment. In this paper, we adapt image mask and original identification of the mask region based convolutional neural networks (R-CNN) to allow recognition at 3 levels such as sequence, holistic and pixel-level semantics. Particularly, pixel and holistic level semantics can be utilized to recognize the texts and define the text shapes, respectively. Precisely, in mask and detection, we segment and recognize both character and word instances. Furthermore, we implement text detection through the outcome of instance segmentation on 2-D feature-space. Also, to tackle and identify the text issues of smaller and blurry texts, we consider text recognition by attention-based of optical character recognition (OCR) model with the mask R-CNN at sequential level. The OCR module is used to estimate character sequence through feature maps of the word instances in sequence to sequence. Finally, we proposed a fine-grained learning technique that trains a more accurate and robust model by learning models from the annotated datasets at the word level. Our proposed approach is evaluated on popular benchmark dataset ICDAR 2013 and ICDAR 2015.&amp;lt;/span&amp;gt;&amp;lt;/p&amp;gt;&lt;/jats:p&gt;</dc:description><dc:publisher>Institute of Advanced Engineering and Science</dc:publisher><dc:date>2023-02-01</dc:date><dc:type>info:eu-repo/semantics/article</dc:type><dc:format>application/pdf</dc:format><dc:identifier>https://doi.org/10.11591/ijece.v13i1.pp413-424</dc:identifier><dc:identifier>10.11591/ijece.v13i1.pp413-424</dc:identifier><dc:source>International Journal of Electrical and Computer Engineering (IJECE); Vol 13 No 1 (2023); 413</dc:source><dc:source>2722-2578</dc:source><dc:source>2088-8708</dc:source><dc:relation>https://ijece.iaescore.com/index.php/IJECE/article/viewFile/26273/16206</dc:relation><dc:rights>http://creativecommons.org/licenses/by-sa/4.0</dc:rights></oai_dc:dc>