Colorizing the dark: AI, Machine/Deep Learning and Visual Tricks to Give (New) Life to Panchromatic Images A new dimension for historical aerial photographs

The most common color space of historical aerial photographs is black and white. For decades archaeologists and photo-interpreters put their efforts in trying to make sense of grayscale variation in cultivated or abandoned field-plots. While in the past, the contrast enhancement of details in panchromatic films should have pass through specific filters for camera lenses during data collection or set different densities in printing phase in dark room, today any digital picture can be easily processed and analyzed with the use of numerous software-filters or algorithms. When dealing with color images, it may be worth trying to convert the photograph into a black and white raster to check whether or not this step improves the marks’ visibility. This paper tries to revert the usual approach by presenting methods to colorize native black and white photographs. The proposed approach, based on available automatic or interactive Artificial Intelligence (Machine Learning or Deep Learning) algorithms, on revised remote sensing procedures and on visual tricks, aims at exploring the possible improvement in readability and interpretation of photographed contests in the usual analytic process. At the same time, colorized historical photographs hold different appeal in the general public and have the potential to attract and involve non-experts in the archaeological/historical reconstruction phases.