Objective

2

As a research branch in the field of image fusion

objective assessment metrics can overcome these shortcomings of subjective evaluation methods that are easily affected by human psychological interference

surrounding environment

and visual characteristics. It can be utilized to evaluate algorithms and design parameters. Our algorithms advantages proposed can be demonstrated via objective assessment metrics. However

there is still a lack of benchmarks and metrics in various application fields like visible and infrared image fusion. A couple of objective assessment metrics can be selected based on prior experience. To facilitate the comparative analysis for different fusion algorithms

our research is focused on a general option method for objective assessment metrics and a set of recommended metrics for the fusion of visible and infrared images.

Method

2

A new selecting method for objective assessment metrics is built. Our method consists of three parts: 1) correlation analysis

2) consistency analysis and 3) discrete analysis. The Kendall correlation coefficient is utilized to perform correlation analysis for all objective assessment metrics. All the objective assessment metrics are clustered according to the value of the correlation coefficient: if the Kendall value of two metrics is higher than the threshold

the two metrics will be put into the same group. The Borda voting method is used in the consistency analysis. There is a ranking for all algorithms in terms of each metric value. An overall ranking is also generated by Borda voting method based on each single ranking of different metrics. The correlation coefficient is used to analyze the consistency between each single ranking and the overall ranking. The objective assessment metric has higher consistency if its correlation coefficient value is higher. Such experiments showed that the metric value will be fluctuated if the fusion quality is changed. A good metric should reflect the fusion quality of different algorithms clearly

so the metric value will cause a large fluctuation in terms of different fusion quality. The different fusion quality we illustrated is originated from multiple algorithms. The coefficient of variation is used to interpret the fluctuation because different objective assessment metrics match different measurement scales. The coefficient of variation reflects overall fluctuations under the influence of the measurement scale. Therefore

the final selected objective assessment metrics set has the following three characteristics: 1) high consistency

2) high coefficient of variation and 3)non-same group.

Result

2

The experiments are conducted on the visible and infrared fusion benchmark (VIFB) dataset. The experiments are segmented into two groups in terms of the visible images in the dataset in related to grayscale images and RGB color images. The recommended objective assessment metric set is under the fusion of visible and infrared image

color visible and infrared image fusion: {standard deviation(SD)

$$Q^{A B / F}$$

} or {SD

$$Q_{\mathrm{CB}}$$

}; gray visible and infrared image fusion: {SD

$$Q^{A B / F}$$

} or {

$$Q_{\mathrm{CB}}$$

}. Under the fusion of color visible and infrared image

both of

$$Q^{A B / F}$$

and

$$Q_{\mathrm{CB}}$$

had good consistency and coefficient of variation within the same group. It did not make much difference to choose each of them. Combining the results of the two sets of experime

nts

{SD

$$Q^{A B / F}$$

} is applied to visible and infrared image fusion. SD is focused on evaluating the contrast information of the fused image

which can intuitively reflect the quality of the fusion of visible and infrared images.

$$Q^{A B / F}$$

is focused on evaluating the edge details. The comparative analysis shows that the algorithms filtered by two objective assessment metrics are similar to the individual subjective evaluation results. The objective assessment metric set selected by our method can be used as a basis for evaluating the performances of visible and infrared fusion algorithms. Compared to the existing methods

this method covers more fusion algorithms and objective assessment metrics without subjective evaluation results.

Conclusion

2

A general selecting method for objective assessment metrics is proposed. The method is not only matched for the fusion of visible and infrared images

but also applies to image fusion in other scenes. Our quick-response method can screen out the most representative objective assessment metric in a scene. Based on the benchmark of visible and infrared image fusion

the recommended representative objective assessment metrics of visible and infrared image fusion are SD and

$$Q^{A B / F}$$

.