Retinex-Based Algorithm to Enhance Underlit Archaeology Images Taken in Semi-or-Fully Enclosed Environments

Abstract

Archaeology is strongly related to digital images, as they visually represent scenes and objects. Archaeological images are rarely obtained in perfect quality, as degradations often affect them. One constant degradation is uneven illumination. It leads to dim, underlit results with unpleasant appearances. This paper provides a fast Retinex-based algorithm to better brighten underlit archaeological images. The Retinex model is adapted using statistical and image processing methods. This aids in providing brighter and more perceptually pleasing results. The main modifications to the Retinex algorithm include the following: (i) utilize a new approach to compute the reflectance component; (ii) add a statistical method to further improve the reflectance; (iii) apply a linear stretching procedure to guarantee full dynamic range pixel distribution. These modifications help to get more uniform illumination in the results. The algorithm efficiently enhanced brightness and tonality, revealing fine textures and intricate details. The resulting images demonstrate significant balance in illumination compared to the original counterparts. Likewise, comparisons are made with six algorithms having dissimilar concepts, and evaluations are made using two assessment methods. The results are promising as the proposed algorithm performed well visually and objectively, scoring an average LOE of 195.14 and average runtime of 0.798 seconds. This indicates a successful tackling of a distinctive challenge, offering a non-complex solution.