A Non-Linear Technique for the Enhancement of Extremely Non-Uniform Lighting Images

At night scenes, either the low intensity areas that are under poor light or the high intensity areas that are overexposed cannot be clearly seen. Various image processing techniques have been developed to recover the meaningful information under extremely low lighting conditions. Among these, the algorithms based on integrated neighborhood dependency of pixel characteristics and based on the illuminance reflectance model perform well for improving the visual quality of digital images captured under nonuniform and extremely low lighting conditions. Although these techniques perform well in low lighting conditions, they cannot perform well in overexposed regions under dark environments such as night driving and night security situations. In this thesis, a new nonlinear image enhancement algorithm, named Multiple Windowed Inverse Sigmoid (MWIS), is proposed for enhancing images captured in extremely non-uniform lighting environments. The proposed algorithm is capable of compressing bright regions and at the same time enhancing dark regions by preserving the main structure of the illuminance-reflectance modality. The main core of the algorithm is a new nonlinear WIS transfer function that is very flexible to enhance the dark regions and compress overexposed regions in an image. It is observed that the proposed algorithm yields visually optimal results on images captured under extreme lighting conditions. Also, it is envisaged that the new technique would be useful for improving the visibility of scenes of night time air force activities.