A new ensemble clustering method for PolSAR image segmentation

Abstract

In this paper, an effort is made to integrate spectral clustering and Gabor feature clustering, leading to improved segmentation results. The spectral clustering divides an image into nonoverlapped groups such that the intragroup similarity is high and the intergroup similarity is low as much as possible. This method includes solving the eigenvalue problem for the normalized similarity matrix, of size n × n, where n is the number of pixels. On the other hand, Gabor filter is used for texture feature extraction. A texture feature vector for each pixel of the image is formed corresponding to the texture edge energy at different directions with Gabor filter. The K-means clustering is applied on the texture feature vectors of all pixel of the input image. Finally, to integrate the results of spectral clustering and Gabor feature clustering, a cluster ensemble approach is applied and PolSAR image segmentation is performed. The experimental results indicate the effect of proposed method on PolSAR image segmentation.

Image segmentation framework based on optimal multi‐method fusion

“…As an important type of images nowadays, synthetic aperture radar (SAR) images got a lot of attention. However, the speckle noise effect on pixel intensities in SAR images makes it hard to segment SAR images precisely [28]. To deal with this issue, a two‐phase algorithm based on Kurtosis curvelet energy and unsupervised spectral regression has been studied [29].…”

Convective cells tracking based on spatio‐temporal context and extended maxima transform using satellite images

“…Akbarizadeh [15] presented a new method to segment SAR images with simple and hard segmentation processing. An integration of spectral clustering and Gabor feature clustering method was proposed for Polarimetric Synthetic Aperture Radar (PolSAR) image segmentation [16]. Akbarizadeh and Rahmani [17] utilised colour features and texture features to segment PolSAR image.…”

Measurement of interphase forces based on dual-modality ERT/DP sensor in horizontal two-phase flow gas-water

“…Alzeyadi et al [23] applied the synthetic aperture radar (SAR) imaging and the K-R-I (curvature-area-amplitude) transform to measure moisture in a concrete panel specimen (water-to-cement ratio = 0.45). Akbarizadeh et al [24] have worked hard to integrate spectral clustering and Gabor feature clustering, leading to improved segmentation results of SAR images. Karimi et al [25] evaluated on two pairs of real radar and optical sentinels and advanced land observation satellite (ALOS) images, and evaluated the impact of RS-LDASR(a new algorithm based on the combination of random subspace (RS), linear discriminant analysis and sparse regularization (LDASR)) on classification results in dimension reduction and supervisory feature selection and learning.…”