Face detection constitutes a pivotal task in computer vision, with its utility extending across security and surveillance, biometrics, human-computer interaction, and entertainment. This technology facilitates the automated recognition and location of human faces within images or videos, a feature instrumental for identification, authentication, and tracking. However, the efficacy of face detection algorithms is compromised under low-light conditions prevalent in CCTV videos, due to variations in illumination levels. To address this challenge, this study introduces a video enhancement method, the Enhanced Deep Curve Estimation (EDCE), designed to augment the quality of low-light CCTV footage, thereby improving face detection accuracy. To circumvent the redundancy of frames during face detection from the input video, a key frame extraction method was employed. Subsequently, the Retina Face was utilized to detect faces from the enhanced CCTV video keyframes. The CCTV videos evaluated in this study were sourced from public cameras, and the performance of the EDCE model was assessed against other existing enhancement models. The findings reveal that the EDCE model exhibits superior performance with a Peak Signalto-Noise Ratio (PSNR) of 21.37 and a Structural Similarity Index Measure (SSIM) of 0.83. Further, the face detection evaluation yielded an Average Precision of 0.847, signifying the effectiveness of our enhancement methodology. This study, thus, underscores the potential of the EDCE model in enhancing the performance of face detection systems under challenging low-light conditions.