The project combines my two principal areas of specialization: (1) architecture history of housing as a large-scale, multifaceted phenomenon; and (2) developing machine-vision archival capabilities for the built environment. Combining methods of computation in architecture with the historiography of the built environment, I attempt to develop an empirical approach to the study of vast urban landscapes using computational capacities. I aim to analyze vast volumes of building data in images, replacing textual keyword labelling by content-based semantic ‘reading’. I use the large corpus of building images from Google Street View to train a convolutional neural network (CNN) model which can identify architectural features in façade images.
