Water Classification Using Convolutional Neural Network

The classification of water sources is a challenging task due to the low contrast texture features, the visual similarities between them, and the causes posed by image acquisition with different camera angles and placements. The various image enhancement techniques, i.e., Unsharp Masking (UM), Histo...

Full description

Saved in:
Bibliographic Details
Main Authors: Saira Asghar, Ghulam Gilanie, Mubbashar Saddique, Hafeez Ullah, Heba G. Mohamed, Irshad Ahmed Abbasi, Mohamed Abbas
Format: Article
Language:English
Published: IEEE 2023-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10190561/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849737142219046912
author Saira Asghar
Ghulam Gilanie
Mubbashar Saddique
Hafeez Ullah
Heba G. Mohamed
Irshad Ahmed Abbasi
Mohamed Abbas
author_facet Saira Asghar
Ghulam Gilanie
Mubbashar Saddique
Hafeez Ullah
Heba G. Mohamed
Irshad Ahmed Abbasi
Mohamed Abbas
author_sort Saira Asghar
collection DOAJ
description The classification of water sources is a challenging task due to the low contrast texture features, the visual similarities between them, and the causes posed by image acquisition with different camera angles and placements. The various image enhancement techniques, i.e., Unsharp Masking (UM), Histogram Equalization (HE), Contrast Limited Adaptive Histogram Equalization (CLAHE), and Contrast Stretching, were used to highlight the contrast and texture features of water images. The enhanced image samples were then fed to the proposed Convolutional Neural Network (CNN)-based model named WaterNet (WNet) for classification. From all employed image enhancement techniques, Contrast Limited Adaptive Histogram Equalization (CLAHE) provides better results in terms of contrast and texture features of water. CLAHE also improved the classification performance of the proposed model, with an accuracy of 97%. For comparison, experiments have also been performed on state-of-the-art pre-trained models, which are DenseNet-201, Inception_ResNet_v2, Inception_v3, and Mobile-Net. Comparison shows that the proposed technique achieves better accuracy in comparison with the state-of-the-art methods.
format Article
id doaj-art-45d441a0bf1440ac9519d3061b0c96cb
institution DOAJ
issn 2169-3536
language English
publishDate 2023-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-45d441a0bf1440ac9519d3061b0c96cb2025-08-20T03:07:01ZengIEEEIEEE Access2169-35362023-01-0111786017861210.1109/ACCESS.2023.329806110190561Water Classification Using Convolutional Neural NetworkSaira Asghar0Ghulam Gilanie1https://orcid.org/0000-0001-6880-8506Mubbashar Saddique2https://orcid.org/0000-0003-4828-5570Hafeez Ullah3https://orcid.org/0000-0003-0640-2628Heba G. Mohamed4https://orcid.org/0000-0002-0443-1049Irshad Ahmed Abbasi5https://orcid.org/0000-0003-1813-1415Mohamed Abbas6Department of Computer Science, The Islamia University of Bahawalpur, Bahawalpur Campus, Bahawalpur, PakistanDepartment of Computer Science, The Islamia University of Bahawalpur, Bahawalpur Campus, Bahawalpur, PakistanDepartment of Computer Science and Engineering, University of Engineering and Technology Lahore, Narowal Campus, Narowal, PakistanDepartment of Physics, The Islamia University Bahawalpur, Bahawalpur Campus, Bahawalpur, PakistanDepartment of Electrical Engineering, College of Engineering, Princess Nourah Bint Abdulrahman University, Riyadh, Saudi ArabiaFaculty of Science and Arts Belqarn, University of Bisha, Sabtul Alaya, Saudi ArabiaElectrical Engineering Department, College of Engineering, King Khalid University, Abha, Saudi ArabiaThe classification of water sources is a challenging task due to the low contrast texture features, the visual similarities between them, and the causes posed by image acquisition with different camera angles and placements. The various image enhancement techniques, i.e., Unsharp Masking (UM), Histogram Equalization (HE), Contrast Limited Adaptive Histogram Equalization (CLAHE), and Contrast Stretching, were used to highlight the contrast and texture features of water images. The enhanced image samples were then fed to the proposed Convolutional Neural Network (CNN)-based model named WaterNet (WNet) for classification. From all employed image enhancement techniques, Contrast Limited Adaptive Histogram Equalization (CLAHE) provides better results in terms of contrast and texture features of water. CLAHE also improved the classification performance of the proposed model, with an accuracy of 97%. For comparison, experiments have also been performed on state-of-the-art pre-trained models, which are DenseNet-201, Inception_ResNet_v2, Inception_v3, and Mobile-Net. Comparison shows that the proposed technique achieves better accuracy in comparison with the state-of-the-art methods.https://ieeexplore.ieee.org/document/10190561/Water sourceswater source classificationwater imagesWaterNet (WNet)image processingimage enhancement techniques
spellingShingle Saira Asghar
Ghulam Gilanie
Mubbashar Saddique
Hafeez Ullah
Heba G. Mohamed
Irshad Ahmed Abbasi
Mohamed Abbas
Water Classification Using Convolutional Neural Network
IEEE Access
Water sources
water source classification
water images
WaterNet (WNet)
image processing
image enhancement techniques
title Water Classification Using Convolutional Neural Network
title_full Water Classification Using Convolutional Neural Network
title_fullStr Water Classification Using Convolutional Neural Network
title_full_unstemmed Water Classification Using Convolutional Neural Network
title_short Water Classification Using Convolutional Neural Network
title_sort water classification using convolutional neural network
topic Water sources
water source classification
water images
WaterNet (WNet)
image processing
image enhancement techniques
url https://ieeexplore.ieee.org/document/10190561/
work_keys_str_mv AT sairaasghar waterclassificationusingconvolutionalneuralnetwork
AT ghulamgilanie waterclassificationusingconvolutionalneuralnetwork
AT mubbasharsaddique waterclassificationusingconvolutionalneuralnetwork
AT hafeezullah waterclassificationusingconvolutionalneuralnetwork
AT hebagmohamed waterclassificationusingconvolutionalneuralnetwork
AT irshadahmedabbasi waterclassificationusingconvolutionalneuralnetwork
AT mohamedabbas waterclassificationusingconvolutionalneuralnetwork