Remote or arial image analysis is one of the vital research area and plays a critical part in object detection and classification. Various image segmentation algorithms have been developed over the years, however, clustering algorithms have an essential role in the segmentation of digital images. Since unsupervised segmentation of images doesn’t require prior knowledge, most of the clustering algorithms employ unsupervised segmentation. It recognizes the hidden patterns of the image to bring feasible outcomes
In DWT, the digital image is divided into four subimages as, A (approximation coefficient or A1 band) contains most of the image information and D
During the period of hypothetical design of the filter, the value of pixel ‘i’ is repaired,
where NL (v) (i) is given by
Where, v is the intensity function, and thus v(j) is the intensity at pixel j and w(i,j) the weight associated with v(j) in the reconstruction of pixel i. The unique description of the fast NLmeans procedure reflects that every pixel can be connected. But virtually, the number of pixels taken into relation in the weighted mean is limited in a neighborhood. The likeness among i and j based on the correspondence of their native regions with mean Euclidean distance
where, z(i) is the normalization constant with
“Distance between
Clustering is the most popular and dynamic research area in statistics, pattern analysis, computer vision, and it aims to cluster similar objects into the same group, and the objects fitting to different clusters are dissimilar. The minimum spanning tree (MST) clustering process can identify the segments of arbitrary shapes by separating the consistent edges in the image. The definition of inconsistent edges is a major issue that has to be addressed in all MSTbased clustering algorithms. Sometimes, the inappropriate number of image clusters, like false edges and excessive boundaries, may lead to oversegmentation
where,
Such that e_{i} is weighted connection among two nearer nodes
The intensity of the pixel at position (x, y) with associated node value is
Correspondingly, nodes in graph G are in a form of
Therefore, the minimum spanning tree of a graph G, and the weight w_{i }connected with edge e_{i} of E' is,
A soft threshold is a preprocessing tool that estimates the optimal thresholding for subbands in the image. Here, imagedenoising is done by either of three methods, namely Sure shrink or Bayesian shrink, or Visual shrink, based on the type of image used in the process. Appropriate filtering is employed by the machine, based on some prior knowledge and the type of the image. It provides image smoothing and better edge preservation. Since filtering is done in the wavelet domain, the detailed coefficients of the decomposed image features are processed, and pixels with intensity values above the threshold values are modified. Subsequently, the shrinkage reduces the noise without distorting the required image features
The subband dependent threshold estimation is given by
in every cycle,
at k^{th} cycle, L_{k} is the extent of subband, and the noise difference
The SRM algorithm belongs to the group of region merging and growing techniques combined with geometric tests to select the merging of a particular region depending on statistical criteria. In the projected study, SRM is employed by considering the segmentation errors while dealing with the clustering process. It would not be possible to separate a limited set of regions during the clustering process. Therefore, these image regions are merged by choosing the suitable decisions in computation of SRM
By considering the regions R׳, R of the digital image IM, if it shares the similar consistency measure, merging criteria is given by
where, . denotes the cardinality and b(R) is given by
Based on the ascending order of the pixel and the difference in pixel intensities between the candidate regions considered for the merging process. The predicate is satisfied with good probability p ≥ 1 − N_for N merge trials,
where, (N) is the number of merging tests and maximum value of N<2 for an image IM
The numbers of regions are varied, based on image and its scaling factor
This paper is organized as follows: The proposed method is discussed in section 2, and section 3 contains the flowchart of the suggested algorithm. The experimental results are given in section 4, and the conclusions are in section 5.
This paper develops a new image segmentation technique based on a machine learning platform. Here random noise is added to the standard arial image. The decomposed image is obtained from Discrete Wavelet Transform (DWT). During preprocessing stage level2 decomposition is carried out, and approximation coefficients are subjected to a fast NLmeans filter, which gives a smoothing effect while preserving edge/texture details. The usage of unsupervised learning for denoised images provides a bettersegmented image. Here MinimumSpanning Tree (MST) clustering technique is mainly used to track the complete object features, which gives more significance to full segmentation as compared to some of the popular segmentation techniques. Further Statistical Region Merging (SRM) approach extracts the required object features of the segmented image and effectively eliminates the oversegmented regions or false boundaries based on probabilistic criteria. Despite the presence of residual noise in detailed coefficients of the decomposed image is filtered automatically by the machine with the help of soft thresholding based on some prior knowledge in structural criteria of image features. Finally, the segmented image is combined with residual image details at wavelet projection, as shown in
Input: standard Arial images are extracted from the SSIP database for analysis and segmentation.
Output: Segmented image.
· A random noise is added to the test image, and the usage of Discrete Wavelet Transform (DWT) provides the decomposed image.
· To reduce the noise, the approximation subimage is subjected to a fast NLmeans filter.
· A Minimum Spanning Tree (MST) clustering approach is assigned to partition the image details, which extract the hidden features of the image.
· The usage of Statistical Region Merging (SRM) helps to reduce the oversegmentation patterns of clustered images.
· Compatible soft threshold filter is assigned based on the structural image criteria is applied by the machine itself with its prior learning
· A combination of wavelet coefficients is displayed into full resolution at the wavelet restoration phase.
In the proposed study, arial images are used for analysis. Here, noisy image is subjected to wavelet domain, a LL subimage is treated with fast NL means filter to achieve better denoising effect, and residual details are filtered automatically by considering the structural criteria of the image based on past learning facts, hence the usage of wavelet domain filtering instead of spatial domain method is a major novelty adopted in preprocessing, before the segmentation stage. The system achieves better segmentation performance by waveletdependent MinimumSpanning Tree (MST) clustering process, coupled with Statistical Region Merging (SRM) is depicted in
Arial image 
Decomposition Level 
Estimated noise standard deviation 
Segmented regions 
Merged regions 
PSNR (dB) 
Time (s) 
7.1.06 
L1 
0.086 
3864 
31 
20.67 
48.35 
L2 
0.086 
1014 
29 
21.72 
17.96 

7.6 
L1 
0.083 
3838 
23 
22.67 
41.45 
L2 
0.082 
1023 
20 
23.68 
19.24 

7.1.01 
L1 
0.089 
3531 
29 
22.48 
38.24 
L2 
0.083 
964 
29 
24.06 
18.43 

7.1.05 
L1 
0.086 
3830 
32 
20.66 
52.09 
L2 
0.087 
1052 
27 
21.42 
35.36 

7.8 
L1 
0.082 
3593 
17 
25.07 
66.17 
L2 
0.082 
990 
13 
26.86 
50.55 

7.1.02 
L1 
0.081 
3422 
24 
26.83 
37.51 
L2 
0.081 
972 
15 
29.01 
24.89 

7.1.03 
L1 
0.081 
3827 
22 
22.60 
43.74 
L2 
0.081 
1012 
21 
23.93 
23.39 
7.1.06 







Level 
2 
2 
2 
2 
2 
2 
2 
Segmented 
254 
94 
350 
256 
244 
225 
1014 
Merged 
120 
163 
191 
174 
166 
16 
29 
PSNR (dB) 
16.89 
20 
21.70 
21.41 
15.11 
14.07 
21.73 
Time(s) 
41.75 
26.64 
22.92 
20.96 
71.13 
16.59 
17.96 
The suggested algorithm is executed in PYTHON (Spyder 3.8), and the simulation results are compared with some of the best methods available in the literature and are found to be significantly better.
Peak signal to noise ratio performs the qualitative and quantitative analysis of denosing algorithms. where L is the highest pixel value and MSE gives mean square error
In this paper, a machine learningbased image clustering technique is developed using wavelet transform. During the preprocessing stage, approximation image coefficients are denoised by a fast NLmeans filter which provides a better denoising effect on random noise compared to other leading methods. A suitable soft thresholding value is automatically selected based on structural criteria of the highfrequency image details is one of the key steps in the proposed algorithm. Here SRM help in eliminating the false boundaries of segmented images and in overcoming the drawbacks of clustering algorithm by reducing the oversegmentation patterns to enhance the necessary hidden image details. Finally, both image features are fused at the wavelet projection level. However, in existing methods especially in arial image analysis, the segmented outcome is not possible to meet the desired level, due to an undersegmentation process. Thus the postprocessing stage produces only a few image features while merging in level2 decomposition. Therefore, the article suggests a new method for standard and Arial image analysis. In the segmentation process, the usage of the clustering technique efficiently segments the crucial details of the denoised image (7.1.06) and significantly overcomes the undersegmentation issues. Therefore the algorithm is more effective in detecting the image patterns as compared to some of the leading segmentation techniques and is one of the major novelty implemented in this work, which helps in the merging process to acquire essential and meaningful features of the segmented image, as shown in Figure 7, 8, and 9. However, the watershedbased hierarchical region merging (HRM) method provides 254 segments and 120 regions, and a graphbased hierarchical region merging approach achieved 350 segments and 94 regions, which were better than Kmeans + HRM, compact watershed + HRM, and quick shift + HRM models. The proposed SRM dependent clustering algorithm achieved 1014 segments and 29 essential object features with residual features is shown in