Byungseok Min

Luminance adapted skin color modeling for the robust detection of skin areas

Statistical models of color channels have been used for the detection of skin areas. However, since the distribution of colors also change as the luminance varies, color distribution models without considering the luminance variation do not work well for the images taken under various illumination conditions. Hence we propose a new skin detection algorithm that considers the luminance value in modeling the color distribution. For implementing this idea, we need a sample of skin color in the image, which can be obtained from the face. It is noted that the faces can be detected without color feature, but by using only structural features such as eyes, mouth, etc. In our algorithm, the eye detector and elliptical boundary are used to detect the face. From the face region, joint Gaussian distributions of color components with respect to the luminance values are obtained. Then, each pixel in the image is classified into skin or non-skin using the statistics obtained from the face region. Experimental results show that the proposed skin color model outperforms the conventional methods in terms of the detection accuracy and F-score.

Quantitative image quality evaluation for mobile display in outdoor environment

The Image quality of a mobile display in outdoor environment is evaluated in quantitative methodology. Contrast and colorfulness were chosen as the main quality factors among several quality attributes such as sharpness, lightness, noise and naturalness, and expressed in Just Noticeable Difference unit to correlate the image quality metric with human visual system. The overall image quality metric is determined by two quality metrics using contrast and colorfulness, respectively. These two quality attributes are obtained from measured XYZ values of the test image on mobile display in outdoor environment.

Hardware-friendly color temperature management for flat panel display

There are demanding display quality factors to meet the industrial requirements for accurate color reproduction such as the chrominance accuracy of primary colors, uniform gray color temperature, display gamma for primary and gray channels and so forth. However, due to the optical limitation of display panels, the correlated color temperature fluctuates up to 3000 Kelvin in typical calibrated flat panel LCD or LED display. The most common method to maintain the constant color temperature is to adjust gamma curves of three primary channels, but it results in the failure of accurate gamma reproduction at the same time. The proposed approach keeps the uniform color temperature for all gray levels while keeping the RGB gamma curves as well as highly saturated colors unchanged, where color changes are made in inverse proportion to the distance from the gray axis. Using the proposed methodology, a new white balancing algorithm is introduced that the white balancing is restricted to near gray colors, not the whole colors in general manners.

Classification of video resolution for the enhanced display of images on HDTV

Although video sources for HDTV broadcasting are mainly in HD resolution, some of them are still from low resolution video sources such as videos that are taken long time ago, internet-streamed or cellphone videos. When these sources are displayed on HDTV, they usually appear to be blurry and their color is not vivid. To alleviate these problems, a proper video enhancement for each source is necessary to display them on HDTV with satisfaction. However, since the decoded images on HDTV do not contain the information on the origin of sources in many cases, it needs to be classified whether their origins out from HD source or not. For this, we propose an HD/non-HD classifier based on the Support Vector Machine (SVM) with the frequency information of the selected region in the decoded image. To evaluate the performance of the proposed HD/non-HD classifier, we use a test database of 6252 HD and 6934 SD still images captured from various TV genres. The experimental results show that the proposed classifier yields high accuracy rate of 99.61%.

Assessment of noise reduction based on human visual system

The performance of the noise reduction algorithm is evaluated by the quality metric using relation between pre-NR and post-NR images. The quality metric in the JND unit reflects the reduction of the block noise visibility and the preservation of the edge sharpness of the contents.