Article Preview
TopYadav et al. (2010) enhanced the visibility level of the foggy image with CLAHE. They enhanced the video quality in real time video system. The video frames are read one at a time. Intensity is adjusted for the foggy frame. First RGB image is converted to gray level and then CLAHE is applied. The resultant enhanced frame is a new structure. Finally, the enhanced De-foggy video is obtained after processing every frame with the above-mentioned step.
Zhao et al. (2010) proposed a novel method to achieve real-time subject-independent automatic facial feature enhancement and detection by combining CLAHE and multi-step integral projection. First, they used a sigma filter to remove noises. After that, they applied CLAHE for enhancing the facial features of the noise-free image obtained from the first step. They then did a multi-step integral projection to detect the useful facial feature regions automatically. Finally, Gabor transformation is used to extract the detected facial feature region and SVM classified the final facial expression recognition. They tested their proposed approach on JAFFE database and claimed a high recognition rate of 95.318% on trained data.
A new method called mixture Contrast Limited Adaptive Histogram Equalization (CLAHE) color models is proposed for underwater image enhancement (Hitam et al., 2013). The proposed method operates CLAHE on RGB and HSV and both the results are combined together using Euclidean norm. The experimental results prove that the proposed approach significantly improves the contrast of underwater images and also reduces noise and artifacts.