Principal Component Analysis-Based Low-Light Image Enhancement Using Reflection Model

In this article, a novel low-light image enhancement (LIME) using reflection model and principal component analysis (PCA) has been proposed. The proposed algorithm works adaptively for dark images based on reflection model and multiscale principle. An input RGB color image is first stretched to correct any type of color distortion and then converted to HSV color space. By using the concept of multiscale theory, the illumination coefficient of the V component is calculated. Then, an image brightness enhancement scheme is employed based on the Fechner principle, which adaptively regulates the parameters of the enhancement function. Further to this, PCA based on image fusion approach is framed to pull out the relevant features from these two images. Finally, the contrast-limited adaptive histogram equalization (CLAHE) model is applied to improve the global contrast. In comparison with other methods, the proposed method gives better outcomes in context of subjective and objective assessments.

Automated summary

The article presents a novel low-light image enhancement method, utilizing reflection model and PCA algorithm for adaptive processing and improvement of global contrast.