Low-light image enhancement plays a crucial role in various computer vision applications, including surveillance, autonomous driving, and medical imaging. Traditional enhancement methods, such as gamma correction, CLAHE, Retinex-based approaches, and LIME, have shown effectiveness in improving brightness and contrast but often introduce artifacts and noise. Recent advancements in deep learning have introduced data-driven methods like Self-Calibrated Illumination (SCI), which offers adaptive enhancement without requiring paired training data. This paper presents a comparative study of traditional and deep learning-based enhancement methods and evaluates their performance using quantitative metrics and visual comparisons. The results demonstrate that deep learning approaches provide superior adaptability and detail preservation compared to traditional methods. Additionally, we discuss the limitations of current techniques and propose possible future directions for improving low-light image enhancement models.