Detection and recognition via adaptive binarization and fuzzy clustering

Research output: Contribution to journalArticle

Abstract

Detection and identification of text in natural scene images pose major challenges: image quality varies as scenes are taken under different conditions (lighting, angle and resolution) and the contained text entities can be in any form (size, style and orientation). In this paper, a robust approach is proposed to localize, extract and recognize scene texts of different sizes, fonts and orientations from images of varying quality. The proposed method consists of the following steps: preprocessing and enhancement of input image using the National Television System Committee (NTSC) color mapping and the contrast enhancement via mean histogram stretching; candidate text regions detection using hybrid adaptive segmentation and fuzzy c-means clustering techniques; a two-stage text extraction from the candidate text regions to filter out false text regions include local character filtering according to a rule-based approach using shape and statistical features and text region filtering via stroke width transform (SWT); and finally, text recognition using Tesseract OCR engine. The proposed method was evaluated using two benchmark datasets: ICDAR2013 and KAIST image datasets. The proposed method effectively dealt with complex scene images containing texts of various font sizes, colors, and orientation; and outperformed state-of-the-art methods, achieving >80% in both precision and recall measures.

Original languageEnglish
Pages (from-to)1759-1781
Number of pages23
JournalPertanika Journal of Science and Technology
Volume27
Issue number4
Publication statusPublished - Oct 2019

Fingerprint

Fuzzy clustering
Cluster Analysis
Color
Television systems
Optical character recognition
Image quality
Stretching
Lighting
Image Enhancement
Engines
Benchmarking
televisions (equipment)
Television
methodology
filters
color
engines
stroke
committees
Stroke

Keywords

  • Adaptive binarization
  • Fuzzy C-means
  • Image enhancement
  • Statistical and geometrical features
  • Text detection
  • Text extraction

ASJC Scopus subject areas

  • Computer Science(all)
  • Chemical Engineering(all)
  • Environmental Science(all)
  • Agricultural and Biological Sciences(all)

Cite this

Detection and recognition via adaptive binarization and fuzzy clustering. / Ismail, Saad Mohmad Saad; Abdullah, Siti Norul Huda Sheikh; Fauzi, Fariza.

In: Pertanika Journal of Science and Technology, Vol. 27, No. 4, 10.2019, p. 1759-1781.

Research output: Contribution to journalArticle

@article{3f1c45aa41fc478eb3717004d30cd574,
title = "Detection and recognition via adaptive binarization and fuzzy clustering",
abstract = "Detection and identification of text in natural scene images pose major challenges: image quality varies as scenes are taken under different conditions (lighting, angle and resolution) and the contained text entities can be in any form (size, style and orientation). In this paper, a robust approach is proposed to localize, extract and recognize scene texts of different sizes, fonts and orientations from images of varying quality. The proposed method consists of the following steps: preprocessing and enhancement of input image using the National Television System Committee (NTSC) color mapping and the contrast enhancement via mean histogram stretching; candidate text regions detection using hybrid adaptive segmentation and fuzzy c-means clustering techniques; a two-stage text extraction from the candidate text regions to filter out false text regions include local character filtering according to a rule-based approach using shape and statistical features and text region filtering via stroke width transform (SWT); and finally, text recognition using Tesseract OCR engine. The proposed method was evaluated using two benchmark datasets: ICDAR2013 and KAIST image datasets. The proposed method effectively dealt with complex scene images containing texts of various font sizes, colors, and orientation; and outperformed state-of-the-art methods, achieving >80{\%} in both precision and recall measures.",
keywords = "Adaptive binarization, Fuzzy C-means, Image enhancement, Statistical and geometrical features, Text detection, Text extraction",
author = "Ismail, {Saad Mohmad Saad} and Abdullah, {Siti Norul Huda Sheikh} and Fariza Fauzi",
year = "2019",
month = "10",
language = "English",
volume = "27",
pages = "1759--1781",
journal = "Pertanika Journal of Science and Technology",
issn = "0128-7680",
publisher = "Universiti Putra Malaysia",
number = "4",

}

TY - JOUR

T1 - Detection and recognition via adaptive binarization and fuzzy clustering

AU - Ismail, Saad Mohmad Saad

AU - Abdullah, Siti Norul Huda Sheikh

AU - Fauzi, Fariza

PY - 2019/10

Y1 - 2019/10

N2 - Detection and identification of text in natural scene images pose major challenges: image quality varies as scenes are taken under different conditions (lighting, angle and resolution) and the contained text entities can be in any form (size, style and orientation). In this paper, a robust approach is proposed to localize, extract and recognize scene texts of different sizes, fonts and orientations from images of varying quality. The proposed method consists of the following steps: preprocessing and enhancement of input image using the National Television System Committee (NTSC) color mapping and the contrast enhancement via mean histogram stretching; candidate text regions detection using hybrid adaptive segmentation and fuzzy c-means clustering techniques; a two-stage text extraction from the candidate text regions to filter out false text regions include local character filtering according to a rule-based approach using shape and statistical features and text region filtering via stroke width transform (SWT); and finally, text recognition using Tesseract OCR engine. The proposed method was evaluated using two benchmark datasets: ICDAR2013 and KAIST image datasets. The proposed method effectively dealt with complex scene images containing texts of various font sizes, colors, and orientation; and outperformed state-of-the-art methods, achieving >80% in both precision and recall measures.

AB - Detection and identification of text in natural scene images pose major challenges: image quality varies as scenes are taken under different conditions (lighting, angle and resolution) and the contained text entities can be in any form (size, style and orientation). In this paper, a robust approach is proposed to localize, extract and recognize scene texts of different sizes, fonts and orientations from images of varying quality. The proposed method consists of the following steps: preprocessing and enhancement of input image using the National Television System Committee (NTSC) color mapping and the contrast enhancement via mean histogram stretching; candidate text regions detection using hybrid adaptive segmentation and fuzzy c-means clustering techniques; a two-stage text extraction from the candidate text regions to filter out false text regions include local character filtering according to a rule-based approach using shape and statistical features and text region filtering via stroke width transform (SWT); and finally, text recognition using Tesseract OCR engine. The proposed method was evaluated using two benchmark datasets: ICDAR2013 and KAIST image datasets. The proposed method effectively dealt with complex scene images containing texts of various font sizes, colors, and orientation; and outperformed state-of-the-art methods, achieving >80% in both precision and recall measures.

KW - Adaptive binarization

KW - Fuzzy C-means

KW - Image enhancement

KW - Statistical and geometrical features

KW - Text detection

KW - Text extraction

UR - http://www.scopus.com/inward/record.url?scp=85074085095&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85074085095&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:85074085095

VL - 27

SP - 1759

EP - 1781

JO - Pertanika Journal of Science and Technology

JF - Pertanika Journal of Science and Technology

SN - 0128-7680

IS - 4

ER -