Analysis of the clustering fusion algorithm for multi-band color image

Jiangchuan Fan; Xinyu Guo; Jianjun Du; Weiliang Wen; Xianju Lu; Brahmani Louiza

doi:10.3934/dcdss.2019085

Article Contents

2019, Volume 12, Issue 4&5: 1233-1249. Doi: 10.3934/dcdss.2019085 open access

This issue Previous Article Reversible hidden data access algorithm in cloud computing environment Next Article Automatic tracking and positioning algorithm for moving targets in complex environment

Analysis of the clustering fusion algorithm for multi-band color image

1.
Beijing Research Center for Information Technology, in Agriculture, Beijing 100097, China
2.
National Engineering Research Center for Information, Technology in Agriculture, Beijing 100097, China
3.
Beijing Key Lab of Digital Plant, Beijing 100097, China
4.
Department of Mathematics and Statistics, The University of North Carolina at Greensboro Greensboro, NC, 27402, United States

* Corresponding author: Xinyu Guo
* Corresponding author: Xinyu Guo

Received: July 31, 2017

Revised: December 31, 2017

Published: March 2019

Abstract Full Text(HTML) Figure(4) / Table(2) Related Papers Cited by

Abstract

Because of the limitations of the technical conditions, the traditional algorithms can not be mapped with many kinds of color, and the treatment effect is poor, which is not conducive to human eye observation. A clustering fusion algorithm based on D-S evidence theory is proposed in this paper to make salt denoising and Gauss denoising operation for the multi-band color image, to improve the image recognition, and better reflect the objective reality, which is not limited by technical conditions; the denoised images are made texture features and edge features extraction; these two kinds of features are fused and carried out the probability distribution to solve the probability of that the each pixel belongs to each class; Based on the DS evidence combination, the probability of four channels is fused, and according to the probability of what kind of each pixel belonging is the largest, it is clustered. Experimental results show that the proposed algorithm can combine different bands of color images to different levels of target features, and retain more effective information, which is conducive to target recognition and detection.

Keywords:

Mathematics Subject Classification: 78A50.

Citation:

FullText(HTML)

Figure 1. SAR image

Download: Full-size image PowerPoint slide

Figure 2. TM image

Download: Full-size image PowerPoint slide

Figure 3. The feature extraction results of the test images by Sobel and Canny operators

Download: Full-size image PowerPoint slide

Figure 4. Comparison results of clustering fusion results by two different algorithms

Download: Full-size image PowerPoint slide

Table 1. Observation parameters of TM image

Sensor	Band	wavelength ($\mu $m)
TM	1	0.45$\sim $0.52 blue light band
	2	0.52$\sim $0.60 green light band
	3	0.63$\sim $0.69 Red band, above the visible light band;
	4	0.76$\sim $0.90 Near infrared band
	5	1.22$\sim $1.75 Middle infrared band
	6	10.4$\sim $12.5 Thermal infrared band
	7	2.08$\sim $2.35 Far infrared band

| Show Table

DownLoad: CSV

Table 2. evaluation index value of clustering fusion of SAR image and TM image

Different algorithms Evaluating indicator		Average gradient	Information entropy	Standard deviation	Edge retention
Traditional algorithm	Band 1	22.5114	7.76	7.0154	52.7669
	Band 4	22.4716	7.72	7.0692	48.2687
	Band 7	21.0537	6.85	6.9837	45.5618
The proposed algorithm	Band 1	32.1645	7.26	6.5945	65.3746
	Band 4	33.0692	7.31	5.8861	62.3149
	Band 7	32.8974	6.43	5.8233	55.8862

| Show Table

DownLoad: CSV

Related Papers

Cited by

References

[1]	R. Adillon and L. Jorba, Quantified trapezoidal fuzzy numbers, Journal of Intelligent & Fuzzy Systems, 33 (2017), 601-611.
[2]	E. Baco, O. Ukimura, E. Rud, L. Vlatkovic, A. Svindland, M. Aron, S. Palmer, T. Matsugasumi, A. Marien and J. C. Bernhard, Magnetic resonance imaging-transectal ultrasound image-fusion biopsies accurately characterize the index tumor: correlation with step-sectioned radical prostatectomy specimens in 135 patients, European Urology, 67 (2015), 787-794.
[3]	I. Barnaure, P. Pollak, S. Momjian, J. Horvath, K. O. Lovblad, C. Bo x, J. Remuinan, P. Burkhard and M. I. Vargas, Evaluation of electrode position in deep brain stimulation by image fusion (mri and ct)., Neuroradiology, 57 (2015), 903-908.
[4]	A. Bicer, Capraro and m.m. capraro, integrated stem assessment model, vol. 13, 2017, 3959-3968.
[5]	M. Bonamy, B. LévÊque and A. Pinlou, Planar graphs with delta $\ge 7$ and no triangle adjacent to a c-4 are minimally edge and total choosable, Discrete Mathematics and Theoretical Computer Science, 17 (2016), 131-145.
[6]	P. S. Brezavscek A. and A. Znidarsic, Factors influencing the behavioural intention to use statistical software: The perspective of the slovenian students of social sciences, Eurasia Journal of Mathematics Science and Technology Education, (), 953-986.
[7]	C. Chen and J. Shi, Chinese local government's behavior in land supply in the context of housing market macro-control, Journal of Interdisciplinary Mathematics, 20 (2017), 1289-1306.
[8]	G. H. Chen, Y. Zhao and B. Su, Raw material inventory optimization for mto enterprises under price fluctuations, Journal of Discrete Mathematical Sciences & Cryptography, 20 (2017), 255-270.
[9]	M. Fei, W. Jiang, W. Mao and Z. Song, New fusional framework combining sparse selection and clustering for key frame extraction, Iet Computer Vision, 10 (2016), 280-287.
[10]	W. Gao and W. Wang, New isolated toughness condition for fractional (g, f, n)-critical graphs, Colloquium Mathematicum, 147 (2017), 55-65. doi: 10.4064/cm6713-8-2016.
[11]	M. Ghahremani and H. Ghassemian, Remote sensing image fusion using ripplet transform and compressed sensing, International Journal of Remote Sensing, 12 (2015), 4131-4143.
[12]	D. Guo, J. Yan and X. Qu, High quality multi-focus image fusion using self-similarity and depth information, Optics Communications, 138-144.
[13]	F. Jing, M. Li, H. J. Zhang and B. Zhang, Spectral clustering image segmentation based on sparse matrix, 4 (2017), 1308-1313.
[14]	Y. Li, C. Jia, X. Kong, L. Yang and J. Yu, Locally weighted fusion of structural and attribute information in graph clustering, IEEE Transactions on Cybernetics, PP (2017), 1-14.
[15]	J. Liang, Y. Han and Q. Hu, Semi-supervised image clustering with multi-modal information, Multimedia Systems, 22 (2016), 149-160.
[16]	H. J. Liu and X. B. Liu, Relationship between paternalistic leadership and employee's voice behavior based on regression analysis, Journal of Discrete Mathematical Sciences & Cryptography, 20 (2017), 205-215.
[17]	P. S., B. M. and R. G., Tephra redeposition and mixing in a late-glacial hillside basin determined by fusion of clustering analyses of glass-shard geochemistry, in Journal of Quaternary Science, 82 (2000), 789-802.
[18]	A. Takahashi, Development status of condensed cluster fusion theory, Current Science, 108 (2015), 514-515.
[19]	B. K. Teh and S. A. Cheong, Cluster fusion-fission dynamics in the singapore stock exchange, European Physical Journal B, 88 (2015), 1-14.
[20]	C. Y. Wang, W. Zhao, Q. Liu and H. W. Chen, Optimization of the tool selection based on big data, Journal of Discrete Mathematical Sciences & Cryptography, 20 (2017), 341-360.
[21]	G. Wei, S. Li and M. R. Farahani, Szeged related indices of tuac6[p, q], Journal of Discrete Mathematical Sciences & Cryptography, 20 (2017), 553-563. doi: 10.1080/09720529.2016.1228312.
[22]	Z. Y. Q. and T. J. L., Clustering sorting algorithm based on digital channelized receiver, Journal of Discrete Mathematical Sciences & Cryptography, 20 (2017), 143-148.
[23]	F. X. Yang, I/o mapping algorithm based on semantic overlay fusion, Bulletin of Science and Technology, 60-62.
[24]	S. Yin, L. Cao, Y. Ling and G. Jin, One color contrast enhanced infrared and visible image fusion method, Infrared & Laser Engineering, 53 (2010), 146-150.
[25]	J. Zhang and H. H. Fan, An improved image segmentation algorithm and simulation based on fuzzy clustering, Computer Simulation.