Hydrophysics

Hydrophysics

Comparison of Canny, Fuzzy Logic, and Supervised Random Forest Classification for Coastline Extraction (Case Study: Bandar Laver)

Document Type : Original Article

Authors
Fateme Bagheri 1
Asghar Milan 2
Alireza Vafaeinejad 1
Mahmood Piroznya 1
1 Faculty of Civil, Water and Environmental Engineering Shahid Beheshti University, Tehran, Iran
2 Faculty of Civil, Water and Environmental, Engineering Shahid Beheshti university, Tehran, Iran.
Abstract
Iran, with more than six thousand kilometers of coastline along the Caspian Sea, Persian Gulf, and Gulf of Oman, ranks among the leading countries worldwide in terms of coastal extent and thus requires effective coastal monitoring and management. Determining and quantifying the coastline position is one of the most important tasks in coastal engineering and management programs. Traditional, field-based shoreline mapping is time-consuming and expensive and cannot meet the demand for continuous monitoring, so there is a growing need for fast, low-cost, and large-area methods such as satellite remote sensing. One effective solution is the extraction of coastlines from satellite imagery using advanced image processing and classification techniques.​ The aim of this study is to extract the coastline of Bandar Laver using three approaches—Canny edge detection, fuzzy logic, and supervised object-oriented classification with the random forest algorithm—and to compare their accuracy in shoreline identification. Sentinel‑2A satellite images were used, and the wet/dry boundary was taken as a proxy for the coastline. Edge detection was applied using the Canny algorithm, while fuzzy logic and object-oriented classification with random forest were implemented to generate shoreline maps, from which the coastline of Bandar Laver was derived for all three methods.​ For validation, the shorelines obtained from the image processing methods were compared with a reference shoreline digitized by an expert interpreter. The overall accuracies were 88% for the Canny method, 90% for the fuzzy logic approach, and 93% for the object-oriented random forest classification, demonstrating the superior performance of the random forest method for coastline extraction in the study area. These results confirm the suitability of object-based machine learning techniques for operational, cost-effective coastal monitoring in Iran.
Keywords
Sentinel images
Canny's algorithm
fuzzy logic
segmentation
object-oriented approach
random forest algorithm

Subjects

[1] Boak EH, Turner IL. Shoreline definition and detection: a review. Journal of coastal research. 2005;21(4):688-703.
[2] Alesheikh AA, Ghorbanali A, Nouri N. Coastline change detection using remote sensing. International Journal of Environmental Science & Technology. 2007;4:61-6.
[3] M.-Muslim A, Foody GM, Atkinson PM. Shoreline mapping from coarse–spatial resolution remote sensing imagery of Seberang Takir, Malaysia. Journal of Coastal Research. 2007;23(6):1399-408.
[4] WILLERSLEV E. Methods of extracting a coastline from satellite imagery and assessing the accuracy. Proceedings of the Geospatial Crossroads GI_Forum. 2011.
[5] Liu H, Jezek KC. A complete high-resolution coastline of Antarctica extracted from orthorectified Radarsat SAR imagery. Photogrammetric Engineering & Remote Sensing. 2004;70(5):605-16.
[6] Guariglia A, Buonamassa A, Losurdo A, Saladino R, Trivigno ML, Zaccagnino A, et al. A multisource approach for coastline mapping and identification of shoreline changes. 2006.
[7] Wang C, Zhang J, Ma Y. Coastline interpretation from multispectral remote sensing images using an association rule algorithm. International Journal of Remote Sensing. 2010;31(24):6409-23.
[8] Mason DC, Davenport IJ. Accurate and efficient determination of the shoreline in ERS-1 SAR images. IEEE Transactions on Geoscience and Remote Sensing. 1996;34(5):1243-53.
[9] Gens R. Remote sensing of coastlines: detection, extraction and monitoring. International Journal of Remote Sensing. 2010;31(7):1819-36.
[10] Zhang H, Jiang Q, Xu J. Coastline extraction using support vector machine from remote sensing image. J Multim. 2013;8(2):175-82.
[11] Hu X, Qin Z, Wang J, Su G, editors. Coastline extraction on remote sensing image using Gaussian process classification. 2015 International Conference on Electromechanical Control Technology and Transportation; 2015: Atlantis Press.
[12] Cassé C, Viet PB, Nhung PTN, Phung HP, Nguyen LD, editors. Remote sensing application for coastline detection in Ca Mau, Mekong Delta2012: Vietnam National University-HCM City Publishing House.
[13] Budhiman S, Parwati E. Digital Image Processing of SPOT-4 for Shoreline Extraction in Lampung Bay. International Journal of Remote Sensing and Earth Sciences (IJReSES). 2017;11(1):1-10.
[14] Boulesteix AL, Janitza S, Kruppa J, König IR. Overview of random forest methodology and practical guidance with emphasis on computational biology and bioinformatics. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery. 2012;2(6):493-507.
[15] Criminisi A, Shotton J, Konukoglu E. Decision forests for classification, regression, density estimation, manifold learning and semi-supervised learning. Microsoft Research Cambridge, Tech Rep MSRTR-2011-114. 2011;5(6):12.
[16] Nitze I, Schulthess U, Asche H. Comparison of machine learning algorithms random forest, artificial neural network and support vector machine to maximum likelihood for supervised crop type classification. Proceedings of the 4th GEOBIA, Rio de Janeiro, Brazil. 2012;79:3540.
[17] Zulkifle FA, Hassan R, Asmuni H, M. Othman R. Shoreline detection, in Tanjung Piai, Malaysia by improving the low brightness and contrast of SPOT-5 images using the NIR-HE method. International Journal of Image and Data Fusion. 2016;7(2):172-88.
[18] Qidwai U, Chen C-h. Digital image processing: an algorithmic approach with MATLAB: CRC press; 2009.
[19] Melin P, Mendoza O, Castillo O. An improved method for edge detection based on interval type-2 fuzzy logic. Expert Systems with Applications. 2010;37(12):8527-35.
[20] Kim D-S, Lee W-H, Kweon I-S. Automatic edge detection using 3× 3 ideal binary pixel patterns and fuzzy-based edge thresholding. Pattern Recognition Letters. 2004;25(1):101-6.
[21] Alshennawy AA, Aly AA. Edge detection in digital images using fuzzy logic technique. International Journal of Computer and Information Engineering. 2009;3(3):540-8.
[22] Ponce-Cruz P, Ramírez-Figueroa FD. Intelligent control for labview: Springer; 2010.
[23] Wang L-X. A course in fuzzy systems. 1999.
[24] Zadeh LA. Fuzzy sets. Information and control. 1965;8(3):338-53.
[25] Cox E, O'Hagan M, Taber R, O'Hagen M. The fuzzy systems handkbook with cdrom: Academic Press, Inc.; 1998.
[26] Sumathi S, Paneerselvam S. Computational intelligence paradigms: theory & applications using MATLAB: crc Press; 2010.
[27] Wang Y, Chen Y. A Comparison of Mamdani and Sugeno Fuzzy Inference Systems for Traffic Flow Prediction. J Comput. 2014;9(1):12-21.
[28] Whiteside T, Ahmad W, editors. A comparison of object-oriented and pixel-based classification methods for mapping land cover in northern Australia. Proceedings of SSC2005 Spatial intelligence, innovation and praxis: The national biennial Conference of the Spatial Sciences Institute; 2005.
[29] Sibaruddin HI, Shafri H, Pradhan B, Haron N, editors. Comparison of pixel-based and object-based image classification techniques in extracting information from UAV imagery data. IOP conference series: earth and environmental science; 2018: IOP Publishing.
[30] Breiman L. Bagging predictors. Machine learning. 1996;24:123-40.
[31] Breiman L. Random forests. Machine learning. 2001;45:5-32.
[32] Saffari A, Leistner C, Santner J, Godec M, Bischof H, editors. On-line random forests. 2009 ieee 12th international conference on computer vision workshops, iccv workshops; 2009: IEEE.
[33] Bosch A, Zisserman A, Munoz X, editors. Image classification using random forests and ferns. 2007 IEEE 11th international conference on computer vision; 2007: Ieee.
[34] Zhou Z-H. Ensemble methods: foundations and algorithms: CRC press; 2012.
[35] Zhou X, Liu X, Zhang Z, editors. Automatic extraction of lakes on the Qinghai-Tibet Plateau from Sentinel-1 SAR images. 2019 SAR in Big Data Era (BIGSARDATA); 2019: IEEE.
[36] Al-Ruzouq R, Shanableh A, Gibril MB, Kalantar B, editors. Multi-scale correlation-based feature selection and random forest classification for LULC mapping from the integration of SAR and optical Sentinel images. Remote Sensing Technologies and Applications in Urban Environments IV; 2019: SPIE.
[37] Baatz M. Multiresolution segmentation: an optimization approach for high quality multi-scale image segmentation. Angewandte geographische informationsverarbeitung. 2000:12-23.
Hydrophysics
Volume 10, Issue 2 - Serial Number 19
September 2025
Pages 85-102

  • Receive Date 16 February 2025
  • Revise Date 10 March 2025
  • Accept Date 08 April 2025