Archiving 4.0: Application of Image Processing and Machine Learning for the Robben Island Mayibuye Archives

Image processing is becoming one of the key technologies of the fourth industrial revolution (4IR) which provides different ways of detecting and recognizing faces, persons and other objects in an image. This can benefit large archives with historical images such as the Robben Island Mayibuye Archives where many figures of the Apartheid struggle appearing in pictures are still unknown. This paper analyzes the findings of the first step of Archiving 4.0, a project that aims of using 4IR techniques to support and improve archiving in South Africa. It aims at finding the best among different models for face detection by evaluating their performance on a subset of the images from the Robben Island Mayibuye Archives. For a range of selected face detection models, the Intersection over Union and the Average Precision are calculated. The models are evaluated and compared on the basis of these metrics and their speed. The results show the strengths and weaknesses of the different approaches and reveal which of the approaches is best to be used in which situation.