Superpixel based graph and random patch for polarimetric SAR image classification
- 1Image Processing and Information Analysis Lab, Faculty of Electrical and Computer Engineering, Tarbiat Modares University
Abstract
Polarimetric synthetic aperture radar (PolSAR) image classification remains challenging due to speckle noise, high dimensionality, and limited labeled data. Most existing methods rely on deep learning models, such as convolutional or graph-based neural networks, which require large annotated datasets and significant computational resources. To address these limitations, this work proposes a non-neural graph-based framework that jointly exploits polarimetric, spatial, and structural information. The image is represented as a superpixel-level graph, where discriminative projections are learned using a superpixel-based discriminant analysis embedded into the graph propagation process. In addition, complementary local texture features are extracted using random patch-based representations. The final feature representation is classified using a support vector machine without any deep network training. Extensive experiments on multiple benchmark PolSAR datasets demonstrate that the proposed method achieves superior performance compared to several state-of-the-art approaches. In particular, it obtains overall accuracies of 99.68% on Flevoland and 95.41% on San Francisco, while using significantly fewer training samples than deep learning-based methods. The results confirm that combining graph-based structural modeling with local patch descriptors provides an effective and label-efficient solution for PolSAR image classification.
Related
- Multimodal patch-based deep learning for early Alzheimer’s disease classification using MRI and PET
- Virtual IHC Synthesis and Bimodal Fusion for Patch-Level Classification of HER2 IHC Expression in Breast Cancer
- Multi-class Alzheimer’s disease classification using VGG19 transfer learning with hybrid Harris Hawks Optimization and random forest
- A hybrid explainable deep learning framework for blood cancer classification using CNN-based feature embeddings and random forest decision models
- Predicting inattention and hyperactivity-impulsivity trajectories using random forest classification in the Adolescent Brain Cognitive Development Study
BibTeX
@article{saneipour2026superpixel,
title = {{Superpixel based graph and random patch for polarimetric SAR image classification}},
author = {Fatemeh Saneipour and Maryam Imani and Hassan Ghassemian},
journal = {Scientific Reports},
year = {2026},
month = jul,
doi = {10.1038/s41598-026-63625-6},
url = {https://doi.org/10.1038/s41598-026-63625-6},
note = {CC BY},
}
RIS
TY - JOUR
TI - Superpixel based graph and random patch for polarimetric SAR image classification
AU - Fatemeh Saneipour
AU - Maryam Imani
AU - Hassan Ghassemian
PY - 2026
DA - 2026/07/01
JO - Scientific Reports
DO - 10.1038/s41598-026-63625-6
UR - https://doi.org/10.1038/s41598-026-63625-6
AB - Polarimetric synthetic aperture radar (PolSAR) image classification remains challenging due to speckle noise, high dimensionality, and limited labeled data. Most existing methods rely on deep learning models, such as convolutional or graph-based neural networks, which require large annotated datasets and significant computational resources. To address these limitations, this work proposes a non-neural graph-based framework that jointly exploits polarimetric, spatial, and structural information. The image is represented as a superpixel-level graph, where discriminative projections are learned using a superpixel-based discriminant analysis embedded into the graph propagation process. In addition, complementary local texture features are extracted using random patch-based representations. The final feature representation is classified using a support vector machine without any deep network training. Extensive experiments on multiple benchmark PolSAR datasets demonstrate that the proposed method achieves superior performance compared to several state-of-the-art approaches. In particular, it obtains overall accuracies of 99.68% on Flevoland and 95.41% on San Francisco, while using significantly fewer training samples than deep learning-based methods. The results confirm that combining graph-based structural modeling with local patch descriptors provides an effective and label-efficient solution for PolSAR image classification.
SN - 2045-2322
ER -