In this paper, we propose a novel pixel-level multi-sensor image fusion algorithm with simultaneous contrast enhancement. In order to accomplish both image fusion and contrast enhancement simultaneously, we suggest a modified framework of the subband-decomposed multiscale retinex (SDMSR), our previous contrast enhancement algorithm. This framework is based on a fusion strategy that reflects the multiscale characteristics of the SDMSR well. We first apply two complementary intensity transfer functions to source images in order to effectively utilize hidden information in both shadows and highlights in the fusion process. We then decompose retinex outputs into nearly nonoverlapping spectral subbands. The decomposed retinex outputs are then fused subband-by-subband, by using global weighting as well as local weighting to overcome the limitations of the pixel-based fusion approach. After the fusion process, we apply a space-varying subband gain to each fused subband-decomposed retinex output according to the subband characteristic so that the contrast of the fused image can be effectively enhanced. In addition, in order to effectively manage artifacts and noise, we make the degree of enhancement of fused details adjustable by improving a detail adjustment function. From experiments with various multi-sensor image pairs, the results clearly demonstrate that even if source images have poor contrast, the proposed algorithm makes it possible to generate a fused image with highly enhanced contrast while preserving visually salient information contained in the source images.

In this letter, we propose a novel contrast enhancement algorithm for optical remote sensing satellite and aerial images. The algorithm is based on multiscale retinex (MSR). Unlike the MSR, however, we first decompose retinex outputs into nearly nonoverlapping spectral subbands. We then apply a space-varying subband gain to each subband-decomposed retinex output by considering its subband characteristic so that the image contrast can be effectively enhanced. In order to improve details in both shadows and highlights, we propose a new hybrid intensity transfer function based on logarithmic functions. In addition, we make the degree of enhancement of details adjustable by introducing a detail adjustment function based on a local standard deviation map of the original image. Experimental results clearly demonstrate that the proposed algorithm effectively distinguishes details in the whole image automatically and greatly enhances the overall contrast in various images.

In color image processing, an image is usually processed in a color space consisting of luminance and chrominance components. The processed result is then converted to the RGB color space for display. However, a straightforward color space conversion can cause color distortion due to gamut difference between the two color spaces. In order to alleviate this gamut problem, we propose two gamut-adaptive correction schemes. For the chrominance component processing, we propose the gamut-adaptive clipping scheme to effectively solve the out-of-gamut problem. For the luminance component processing of a color image, we propose the gamut-adaptive scaling scheme to alleviate both the out-of-gamut and under-saturation problems. The proposed methods can be applied for image processing in any color space since the proposed correction is performed in the RGB color space. Experimental results show that the proposed methods can preserve the luminance and hue values and provide rich colors by adaptively controlling the saturation value according to the luminance component value.

This paper presents a novel multi-sensor image fusion algorithm to generate a contrast-enhanced fused image. The algorithm is based on a framework of the subband decomposed multiscale retinex (SD-MSR) that is one of the contrast enhancement methods. It also uses two complementary intensity transfer functions to enhance the details in both shadows and highlights. For effective contrast enhancement, we suggest a novel fusion strategy which reflects the characteristics of SD-MSR well. Thereby, even if input images have poor contrast, the proposed algorithm is able to generate a fused image with highly enhanced contrast. Experimental results demonstrate that the algorithm performs well for generating high contrast fused images.

In this paper, we propose a novel image enhancement algorithm by improving the standard multiscale retinex (MSR) algorithm. A modified retinex output using a combination of two logarithmic functions enhances the details in highlights as well as the details in shadows. Sub-band decomposition of the modified retinex output makes the individual gain control of spectral bands possible, so that we can enhance image details according to band characteristics. Due to the effective sub-band based gain control, the final enhanced image can be automatically obtained without a user-assisted "canonical" gain/offset control. Experimental results clearly demonstrate that the proposed algorithm effectively distinguishes the details in both highlights and shadows and greatly enhances the overall contrast while maintaining a natural scene.

In multi-sensor image fusion, multi-resolution approaches became popular because they can preserve detailed information well. Among them, the gradient-based multi-resolution (GBMR) algorithm is known to effectively reduce ringing artifacts near edges compared with the discrete wavelet transform (DWT)-based algorithm. However, since the GBMR algorithm does not consider the diagonal direction, the ringing artifacts reduction is not satisfactory at diagonal edges. In this paper, we generalize the GBMR algorithm by adopting the wavelet structure. Thereby, the proposed algorithm improves the fusion process in high-frequency sub-bands so as to preserve details of input images. Meanwhile, the algorithm fuses the low-frequency sub-band by considering the overall contrast in the output image. To evaluate the proposed algorithm, we compare it with the DWT-based and GBMR algorithms. Experimental results clearly demonstrate that the proposed algorithm effectively reduces ringing artifacts for edges of all directions and greatly enhances the overall contrast while minimizing visual information loss.