Face detection applications often struggle to identify human features in dark or extremely low-contrast images captured in nighttime environments. This research explores an experimental approach to overcoming illumination challenges using three primary image processing techniques: Contrast Stretching, Histogram Equalization, and Adaptive Equalization. The paper illustrates a proposed algorithm and working procedure that differentiates pixel intensity across various stages of processing to reveal hidden facial features. Conducted from a practical application perspective, the study demonstrates how software can successfully detect human faces from photos captured in excessive darkness or low-light conditions. By analyzing the efficacy of these enhancement methods, the research provides a foundation for improving computer vision systems used in surveillance, security, and mobile photography within challenging lighting environments. The findings contribute to the field of computer vision by establishing a robust methodology for face detection where standard light-sensitive algorithms typically fail.

Keywords: Image Processing, Dark Image, Face Detection, Low-Contrast Image, Computer Vision, Histogram Equalization, AUB.