Local Contrast Enhancement Based on Adaptive Multi-Scaled Retinex using Intensity Distribution of Input Image

As the dynamic range of a digital camera is narrower than that of a real scene, the captured image requires a tone curve or contrast correction to reproduce the information in dark regions. Yet, when using a global correction method, such as histogrambased methods and gamma correction, an unintended contrast enhancement in bright regions can result. Thus, a multiscale retinex algorithm using Gaussian filters was already proposed to enhance the local contrast of a captured image using the ratio between the intensities of an arbitrary pixel in the captured image and its surrounding pixels. The intensity of the surrounding pixels is estimated using Gaussian filters and weights for each filter, and to obtain better results, these Gaussian filters and weights are adjusted in relation to the captured image. Nonetheless, this adjustment is currently a subjective process, as no method has yet been developed for optimizing the Gaussian filters and weights according to the captured image. Therefore, this article proposes local contrast enhancement based on an adaptive multiscale retinex using a Gaussian filter set adapted to the input image. First, the weight of the largest Gaussian filter is determined using the local contrast ratio from the intensity distribution of the input image. The other Gaussian filters and weights for each Gaussian filter in the multiscale retinex are then determined using a visual contrast measure and the maximum color difference of the color patches in the Macbeth color checker. The visual contrast measure is obtained based on the product of the local standard deviation and locally averaged luminance of the image. Meanwhile, to evaluate the halo artifacts generated in large uniform regions that abut to form a high contrast edge, the artifacts are evaluated based on the maximum color difference between each color of the pixels in a patch in the Macbeth color and the averaged color in CIELAB standard color space. When considering the color difference for halo artifacts, the parameters for the Gaussian filters and weights representing a higher visual contrast measure are determined using test images. In addition, to reduce the induced graying-out, the chroma of the resulting image is compensated by preserving the chroma ratio of the input image based on the maximum chroma values of the sRGB color gamut in the lightness–chroma plane. In experiments, the proposed method is shown to improve the local contrast and saturation in a natural way. VC 2011 Society for Imaging Science and Technology. [DOI: 10.2352/J.ImagingSci.Technol.2011.55.4.040502] INTRODUCTION Human vision is a complicated automatic self-adapting system that is capable of seeing over 5 orders of magnitude simultaneously and can gradually adapt to natural world scenes with a high dynamic range of over 9 orders of magnitude. Thus, human vision can concurrently perceive details in both bright and dark regions. In contrast, current color imaging capture and display devices, such as digital cameras, cathode ray tubes (CRTs), liquid crystal displays (LCDs), plasma display panels (PDPs), and organic light-emitting diodes (OLEDs), are unable to capture and represent a dynamic range of more than 100:1. This means that the captured images suffer from poor scene detail and color reproduction in dark areas, especially in the case of a scene that contains both bright and dark areas. Nonetheless, despite the need to adjust the contrast of an image captured by a digital camera to represent the viewer’s perception of the natural scene, this remains a difficult problem, insofar as the human visual system is extremely complex and current techniques are unable to replicate it completely. As the sensitivity of the human eye changes locally according to the position of an object and the illuminant in the scene, a spatially adaptive method is required to overcome these limitations, which has led to the recent development of the single-scale retinex model, based on the retinex theory as a model of human vision perception. The singlescale retinex model utilizes the ratio of the lightness for a small central field in the region of interest to the average lightness over an extended field, where a Gaussian filter is generally used to obtain the average lightness. However, application of the single-scale retinex model introduces several problems, such as halos and graying-out, depending on the size of the Gaussian filter, which varies according to