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 UNcamp 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-f001: An example on UNcamp 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 1 is an example of infrared and visual image fusion of the UNcamp images. Infrared and visual image fusion should effectively combine the image regions and details in the original images into the final fusion image. Thus, the fusion image should be clear and contain rich image details, which is useful for the further image analysis. Because some details are still smoothed, the results of MSTHT, MSTHST and MSNTHT are not clear and the details of the results of SIDWT and LP are also not clear and even worse than the result of MSTHST. The result of MSTOOC contains more details than the results of MSTHT, SIDWT, LP, MSTHST and MSNTHT, which is clearer. However, the result of the proposed algorithm is the clearest and it contains the richest image details. Therefore, the proposed algorithm performs better for infrared and visual image fusion than other algorithms.


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

Bai X - Sensors (Basel) (2015)

An example on UNcamp 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-f001: An example on UNcamp 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 1 is an example of infrared and visual image fusion of the UNcamp images. Infrared and visual image fusion should effectively combine the image regions and details in the original images into the final fusion image. Thus, the fusion image should be clear and contain rich image details, which is useful for the further image analysis. Because some details are still smoothed, the results of MSTHT, MSTHST and MSNTHT are not clear and the details of the results of SIDWT and LP are also not clear and even worse than the result of MSTHST. The result of MSTOOC contains more details than the results of MSTHT, SIDWT, LP, MSTHST and MSNTHT, which is clearer. However, the result of the proposed algorithm is the clearest and it contains the richest image details. Therefore, the proposed algorithm performs better for infrared and visual image fusion than other algorithms.

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