Search

In this study, focusing on the fact that the intensity histogram of a backlit image shows a characteristic bimodal distribution, we propose an image enhancement method for single backlit images using histogram specification. In general, well-known histogram equalization-based techniques are powerful in image enhancement, but when simply applied to backlit images, they often change the overall appearance and also highlight unnaturalness. In the proposed method, a target shape of the intensity histogram that improves the bimodal distribution is determined, and then intensity conversion by histogram specification is conducted while preserving hue and saturation. The effectiveness of the proposed method is verified through a series of comparative experiments.

The color image enhancement is one of the most important image processing techniques and is utilized to improve the visibility of digital images in various situations. In this paper, we propose a novel hue-preserving color image enhancement method which is executed on a vector space of convex combination coefficients and does not generate the color gamut problem. In the proposed method, at first, each pixel of an input image is represented by a convex combination of white, black, and its pure color. Then the combination coefficients are transformed by the histogram specification technique using the gradient norm-based weighted histograms of the coefficients, and the distributions of the coefficients are expanded to enhance the both of image intensity and saturation components appropriately. Through the experiments employing various color images, the effectiveness of the proposed method is verified.

The dynamic range of human light perception for natural scenes is wider than the dynamic ranges of cameras. When an image of a natural scene is taken by a camera, the image may contain under-exposed or over-exposed regions. A remedy for this problem is to fuse multi-exposure images which are taken by the camera at different exposure levels. Since most fusion methods use a weighted average of multi-exposure images, the appropriate calculation of its weights is important. In this paper, we propose a method for fusing multi-exposure images which are newly generated by a light conversion with preserving hue and saturation. In the proposed method, the lightness conversion is based on local color correction (LCC) and a fused image is obtained by a weighted average whose weights are calculated based on saturation. The proposed method is applied to several images and the effectiveness of the proposed method is investigated.

Generally, in color image contrast enhancement, the intensity or saturation component of an image is processed without the change of hue component of the image. In some color space used for contrast enhancement, processed pixel values are located outside of the gamut of the RGB color space. In that case, a clipping process is required to make the pixel values located inside of the gamut. However, the clipping process changes the combination of R, G, and B components and causes unexpected hue changes. In the present paper, we propose a hue-preserving contrast enhancement method for color images without gamut problem. In the proposed method, the contrast enhancement of a color image is realized by spreading out the distribution of pixel values on a constant hue plane in the RGB color space. The constant hue plane is represented as the triangle whose vertices correspond to white, black, and the maximally saturated colors. By spreading out the distribution of the pixel values on the constant hue plane, a remedy for the gamut problem and hue-preserving contrast enhancement are realized. Through experiments, the effectiveness of the proposed method is verified.

White balance (WB) is the correction process to remove unrealistic color casts caused by an illuminant color. For high-quality image correction, it is important to accurately estimate the illuminant color. In this study, we propose an accurate illuminant color estimation method for WB based on pseudo-detection of specular reflection. In the proposed method, pixels which are brighter than their neighborhood and their neighboring darker pixels are found at first. Then, the averages of their pixel values are calculated respectively, and then the specular reflection is detected approximately as the difference of the average values. Finally, the illuminant color is estimated as the specular reflection itself. The accurate estimation capability of the proposed method is verified through a series of comparative experiments with typical WB methods.

The signal sources localization is a very important study, and many researchers work on this problem by various methods. A genetic algorithm (GA) is probabilistic search method based on a process of the evolution. GA is applied to many real problems, because it has high versatility and search ability. However, in the conventional GA, the reproduction operator causes a lack of genetic diversity, and search efficiency decreases. To solve this problem, the GA in consideration of genetic diversity was proposed. This method can search the optimal solution faster than a conventional GA. However, the parameter which define a degree of variability have to be decided depending on a given problem. In this paper, we propose the new method in which the degree of variability can be adaptively defined based on the fitness values and the spatial distribution of the individuals. The effectiveness of the proposed method is verified by applying it to the signal sources localization using a simple head model.

Nowadays, digital images can be easily obtained, recorded and processed in accordance with the widespread use of digital cameras and personal computers. There is an image enhancement as one of most general image processing techniques. In the image enhancement, unsharp masking (UM) has been used widely because its algorithm is very simple and can produce good results. However, over-enhancement occurs in edge parts of the image. Additionally UM also is easy to generate artifacts such as jaggy and halo. To cope with these problems, the authors proposed the selective UM method based on the edge-preserved smoothing filter. However, the image quality obtained by our method depends on values of the enhancement parameters, and their optimal values vary according to user's liking. In this paper, we propose an image enhancement system considering the user's liking by using an interactive genetic algorithm (IGA). In the proposed system, the IGA optimizes the parameters of the image enhancement. Further, a new genetic operation is introduced in order to achieve the effective search in the IGA of the proposed system. Through the experiments using some images, the effectiveness of the proposed system is verified.