Dual Illumination Image Enhancement Using Automated MSRCR and Illumination Estimation
Allysa Kate M. Brillantes, Edwin Sybingco, Argel Alejandro Bandala, Robert Kerwin C. Billones, Alexis M. Fillone, Elmer P. Dadios · 2023
Images taken in low-light environments like nighttime or cloudy weather are not conducive to monitoring and fail to fulfill the requirements of applications such as image processing and computer vision. This paper focuses on improving a dual illumination image enhancement algorithm to achieve better image quality and reduce the processing time of producing an enhanced image. The underexposed correction image was produced using Automated Multiscale Retinex Color Restoration while the overexposed correction image was produced using illumination estimation, the corrected images were combined to generate a better-quality image. The system was assessed using the metrics: BRISQUE, NIQE, MDM, and CEIQ, and achieved a BRISQUE value of 18.628, NIQE value of 1.744, MDM value of 0.968, and CEIQ value of 3.615.