A digital archieve or the future of architectural archieves - a new research grant from the Ministry of Science

We are glad to share that we have been awarded a new grant in collaboration with Prof. Yael Alweill from the Technion. This proposal's research offers a new approach to architectural archiving concerning the pictorial (rather than textual) nature of documentation of the built environment. We combine computation methods in architecture with the historiography of the built environment towards developing a new methodology for architectural archiving, the Future_ARChive.

The history of architecture has traditionally been discussed using a canon of buildings and built environments by building type, architect, or historical period/style. Nonetheless, the proliferation of digital images produced and stored by users and services on the internet provides an opportunity to reconsider this formulation of the architectural canon. Scholars cannot ignore these new forms of image-making. However, classifying and organizing these millions of pictures requires advancement beyond keyword-based archival methods toward meaningful semantic reading and categorization of images, which remains a significant open problem.

Recent advances in the field of Computer Vision have made it possible to recognize and classify objects in pictures (e.g., faces and animals) by the use of Convolutional Neural Networks (CNN). They offer a new approach to constructing an archive that could contribute significantly to studying the built environment. We propose a methodology to replace textual keyword labeling with semantic labeling toward image recognition of the built environment. This methodology is developed employing a case study involving identifying and classifying buildings of the postmodern period in Tel Aviv in collaboration with the city's Conservation Department. Even though this type of research question would typically fall
within the field of architectural history, we have re-imagined it as a problem at the intersection of architectural computing and architectural history. This project's conceptual and technical challenges lie at the intersection of these two fields and cannot be considered in isolation
in either field.

More details are on the research page.