Image registration has always been the hot topic in image research field, and the mutual information registration method has become a commonly used method in image registration because of its high precision and good robustness. Unfortunately, it has a problem for infrared and visible image registration. Lots of rich background detail information is usually provided by the visible light band, while the infrared image can locate an object (heat source) with a higher temperature, and often can't obtain the background information. The large difference in the background information of the two images not only interferes with the accuracy of the registration algorithm but also brings a lot of computation. In this paper, a method of fuzzy c-means clustering is used to separate foreground and background which reduces the background information interference for registration, based on the feature that the infrared image and the visible image have a high uniformity in the target area and a large difference in the background area. Then, the mutual information of the foreground image marked by clustering algorithm is calculated as the similarity measure to achieve the purpose of registration. Finally, the algorithm is tested by the infrared and visible images acquired actually. The results show that the two image’s registration is perfectly implemented and verify the effectiveness of this method.
In a low-light scene, capturing color images needs to be at a high-gain setting or a long-exposure setting to avoid a visible flash. However, such these setting will lead to color images with serious noise or motion blur. Several methods have been proposed to improve a noise-color image through an invisible near infrared flash image. A novel method is that the luminance component and the chroma component of the improved color image are estimated from different image sources . The luminance component is estimated mainly from the NIR image via a spectral estimation, and the chroma component is estimated from the noise-color image by denoising. However, it is challenging to estimate the luminance component. This novel method to estimate the luminance component needs to generate the learning data pairs, and the processes and algorithm are complex. It is difficult to achieve practical application. In order to reduce the complexity of the luminance estimation, an improved luminance estimation algorithm is presented in this paper, which is to weight the NIR image and the denoised-color image and the weighted coefficients are based on the mean value and standard deviation of both images. Experimental results show that the same fusion effect at aspect of color fidelity and texture quality is achieved, compared the proposed method with the novel method, however, the algorithm is more simple and practical.