Staff View: DCT-DWT-FFT based method for text detection in underwater images

DCT-DWT-FFT based method for text detection in underwater images

Text detection in underwater images is an open challenge because of the distortions caused by refraction, absorption of light, particles, and variations depending on depth, color, and nature of water. Unlike existing methods aimed at text detection in natural scene images, in this paper, we have pro...

Full description

Saved in:

Bibliographic Details
Main Authors:	Banerjee, Ayan, Shivakumara, Palaiahnakote, Pal, Soumyajit, Pal, Umapada, Liu, Cheng-Lin
Format:	Conference or Workshop Item
Published:	SPRINGER INTERNATIONAL PUBLISHING AG 2022
Subjects:	QA75 Electronic computers. Computer science
Online Access:	http://eprints.um.edu.my/41004/
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my.um.eprints.41004
record_format	eprints
spelling	my.um.eprints.410042025-02-25T04:47:06Z http://eprints.um.edu.my/41004/ DCT-DWT-FFT based method for text detection in underwater images Banerjee, Ayan Shivakumara, Palaiahnakote Pal, Soumyajit Pal, Umapada Liu, Cheng-Lin QA75 Electronic computers. Computer science Text detection in underwater images is an open challenge because of the distortions caused by refraction, absorption of light, particles, and variations depending on depth, color, and nature of water. Unlike existing methods aimed at text detection in natural scene images, in this paper, we have proposed a novel method for text detection in underwater images through a new enhancement model. Based on observations that fine details of text in image share with high energy, spatial resolution, and brightness, we consider Discrete Cosine Transform (DCT), Discrete Wavelet Transform (DWT), and Fast Fourier Transform (FFT) for image enhancement to highlight the text features. The enhanced image is fed to a modified Character Region Awareness for Text Detection (CRAFT) model to detect text in underwater images. To explore enhancement methods, we evaluate six combinations of image enhancement techniques, namely, DCT-DWT-FFT, DCT-FFT-DWT, DWT-DCT-FFT, DWT-FFT-DCT, FFT-DCT-DWT, FFT-DWTDCT. Experimental results on our dataset of underwater images and benchmark datasets of natural scene text detection, namely, MSRA-TD500, ICDAR 2019 MLT, ICDAR 2019 ArT, Total-Text, CTW1500, and COCO Text show that the proposed method performs well for both underwater and natural scene images and outperforms the existing methods on all the datasets. SPRINGER INTERNATIONAL PUBLISHING AG 2022 Conference or Workshop Item PeerReviewed Banerjee, Ayan and Shivakumara, Palaiahnakote and Pal, Soumyajit and Pal, Umapada and Liu, Cheng-Lin (2022) DCT-DWT-FFT based method for text detection in underwater images. In: 6th Asian Conference on Pattern Recognition, ACPR 2021, 9-12 November 2021, Virtual, Online.
institution	Universiti Malaya
building	UM Library
collection	Institutional Repository
continent	Asia
country	Malaysia
content_provider	Universiti Malaya
content_source	UM Research Repository
url_provider	http://eprints.um.edu.my/
topic	QA75 Electronic computers. Computer science
spellingShingle	QA75 Electronic computers. Computer science Banerjee, Ayan Shivakumara, Palaiahnakote Pal, Soumyajit Pal, Umapada Liu, Cheng-Lin DCT-DWT-FFT based method for text detection in underwater images
description	Text detection in underwater images is an open challenge because of the distortions caused by refraction, absorption of light, particles, and variations depending on depth, color, and nature of water. Unlike existing methods aimed at text detection in natural scene images, in this paper, we have proposed a novel method for text detection in underwater images through a new enhancement model. Based on observations that fine details of text in image share with high energy, spatial resolution, and brightness, we consider Discrete Cosine Transform (DCT), Discrete Wavelet Transform (DWT), and Fast Fourier Transform (FFT) for image enhancement to highlight the text features. The enhanced image is fed to a modified Character Region Awareness for Text Detection (CRAFT) model to detect text in underwater images. To explore enhancement methods, we evaluate six combinations of image enhancement techniques, namely, DCT-DWT-FFT, DCT-FFT-DWT, DWT-DCT-FFT, DWT-FFT-DCT, FFT-DCT-DWT, FFT-DWTDCT. Experimental results on our dataset of underwater images and benchmark datasets of natural scene text detection, namely, MSRA-TD500, ICDAR 2019 MLT, ICDAR 2019 ArT, Total-Text, CTW1500, and COCO Text show that the proposed method performs well for both underwater and natural scene images and outperforms the existing methods on all the datasets.
format	Conference or Workshop Item
author	Banerjee, Ayan Shivakumara, Palaiahnakote Pal, Soumyajit Pal, Umapada Liu, Cheng-Lin
author_facet	Banerjee, Ayan Shivakumara, Palaiahnakote Pal, Soumyajit Pal, Umapada Liu, Cheng-Lin
author_sort	Banerjee, Ayan
title	DCT-DWT-FFT based method for text detection in underwater images
title_short	DCT-DWT-FFT based method for text detection in underwater images
title_full	DCT-DWT-FFT based method for text detection in underwater images
title_fullStr	DCT-DWT-FFT based method for text detection in underwater images
title_full_unstemmed	DCT-DWT-FFT based method for text detection in underwater images
title_sort	dct-dwt-fft based method for text detection in underwater images
publisher	SPRINGER INTERNATIONAL PUBLISHING AG
publishDate	2022
url	http://eprints.um.edu.my/41004/
_version_	1825160582171459584
score	13.244109

DCT-DWT-FFT based method for text detection in underwater images

Similar Items