Limits...
Infrared and Visual Image Fusion through Fuzzy Measure and Alternating Operators.

Bai X - Sensors (Basel) (2015)

Bottom Line: Firstly, the alternating operators constructed using the opening and closing based toggle operator are analyzed.Thirdly, the extracted multi-scale features are combined through the fuzzy measure-based weight strategy to form the final fusion features.All the experimental results indicate that the proposed algorithm is effective for infrared and visual image fusion.

View Article: PubMed Central - PubMed

Affiliation: Image Processing Center, Beijing University of Aeronautics and Astronautics, Beijing 100191, China. jackybxz@buaa.edu.cn.

ABSTRACT
The crucial problem of infrared and visual image fusion is how to effectively extract the image features, including the image regions and details and combine these features into the final fusion result to produce a clear fused image. To obtain an effective fusion result with clear image details, an algorithm for infrared and visual image fusion through the fuzzy measure and alternating operators is proposed in this paper. Firstly, the alternating operators constructed using the opening and closing based toggle operator are analyzed. Secondly, two types of the constructed alternating operators are used to extract the multi-scale features of the original infrared and visual images for fusion. Thirdly, the extracted multi-scale features are combined through the fuzzy measure-based weight strategy to form the final fusion features. Finally, the final fusion features are incorporated with the original infrared and visual images using the contrast enlargement strategy. All the experimental results indicate that the proposed algorithm is effective for infrared and visual image fusion.

No MeSH data available.


Related in: MedlinePlus

An example on Dune images. (a) Original infrared image (b) Original visual image (c) Result of MSTHT; (d) Result of SIDWT (e) Result of LP (f) Result of MSTHST; (g) Result of MSNTHT (h) Result of MSTOOC (i) Result of the proposed algorithm.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4541927&req=5

sensors-15-17149-f002: An example on Dune images. (a) Original infrared image (b) Original visual image (c) Result of MSTHT; (d) Result of SIDWT (e) Result of LP (f) Result of MSTHST; (g) Result of MSNTHT (h) Result of MSTOOC (i) Result of the proposed algorithm.

Mentions: Figure 2 is an example of infrared and visual image fusion of the Dune images. The original images are not clear. Although MSTHT, SIDWT and LP combine the original infrared and visual images, some details are still smoothed, which results in a not very clear image. The result of MSNTHT is clearer than MSTHT, and the contrast is good, but the details are still not very clear. The results of MSTHST and MSTOOC are good and the details are clear. However, comparing with the result of the proposed algorithms, the details of the results of MSTHST and MSTOOC are not very clear. Especially, the details in the result of the proposed algorithm are very rich and the result is clearer than the results of other algorithms. These indicate the better performance of the proposed algorithm.


Infrared and Visual Image Fusion through Fuzzy Measure and Alternating Operators.

Bai X - Sensors (Basel) (2015)

An example on Dune images. (a) Original infrared image (b) Original visual image (c) Result of MSTHT; (d) Result of SIDWT (e) Result of LP (f) Result of MSTHST; (g) Result of MSNTHT (h) Result of MSTOOC (i) Result of the proposed algorithm.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4541927&req=5

sensors-15-17149-f002: An example on Dune images. (a) Original infrared image (b) Original visual image (c) Result of MSTHT; (d) Result of SIDWT (e) Result of LP (f) Result of MSTHST; (g) Result of MSNTHT (h) Result of MSTOOC (i) Result of the proposed algorithm.
Mentions: Figure 2 is an example of infrared and visual image fusion of the Dune images. The original images are not clear. Although MSTHT, SIDWT and LP combine the original infrared and visual images, some details are still smoothed, which results in a not very clear image. The result of MSNTHT is clearer than MSTHT, and the contrast is good, but the details are still not very clear. The results of MSTHST and MSTOOC are good and the details are clear. However, comparing with the result of the proposed algorithms, the details of the results of MSTHST and MSTOOC are not very clear. Especially, the details in the result of the proposed algorithm are very rich and the result is clearer than the results of other algorithms. These indicate the better performance of the proposed algorithm.

Bottom Line: Firstly, the alternating operators constructed using the opening and closing based toggle operator are analyzed.Thirdly, the extracted multi-scale features are combined through the fuzzy measure-based weight strategy to form the final fusion features.All the experimental results indicate that the proposed algorithm is effective for infrared and visual image fusion.

View Article: PubMed Central - PubMed

Affiliation: Image Processing Center, Beijing University of Aeronautics and Astronautics, Beijing 100191, China. jackybxz@buaa.edu.cn.

ABSTRACT
The crucial problem of infrared and visual image fusion is how to effectively extract the image features, including the image regions and details and combine these features into the final fusion result to produce a clear fused image. To obtain an effective fusion result with clear image details, an algorithm for infrared and visual image fusion through the fuzzy measure and alternating operators is proposed in this paper. Firstly, the alternating operators constructed using the opening and closing based toggle operator are analyzed. Secondly, two types of the constructed alternating operators are used to extract the multi-scale features of the original infrared and visual images for fusion. Thirdly, the extracted multi-scale features are combined through the fuzzy measure-based weight strategy to form the final fusion features. Finally, the final fusion features are incorporated with the original infrared and visual images using the contrast enlargement strategy. All the experimental results indicate that the proposed algorithm is effective for infrared and visual image fusion.

No MeSH data available.


Related in: MedlinePlus