Arthistoric Analysis of Architecture via Computer Vision
Björn Ommer, Peter Bell & Michael Arnold
Inovation Fund FRONTIER, Heidelberg University funded by German Research Foundation (DFG)
The interdisciplinary Frontier project connects computer vision with the field of art history and analyses early modern architecture with the help of machine learning and image processing.
Our approach is initially based on a small database of 1324 images. The collection contains photographs of early modern facades, illustrations from architectural treatises, drawings, and book illustrations from the British Library.
|Fig 1. A search for a balustrade shows a good variation of results. However one also finds typical examples for false positives.|
The Frontier project divides its research into three tasks. The first task is to detect entire buildings or parts of buildings. This is done either by selecting a part of an existing image or by uploading a new image.
|Fig 2. Search results of Corinthian Capitals. Undeniably, images of Composite Capitals are mixed in with the results.|
|Fig 3. The algorithm is especially successful in the search for rather uncommon Orders.|
An offline pool of prototypical negative examples of early modern architecture is created once on the database. This allows the user to search for an arbitrary selection of the image. Every search request performed by the user is then compared with the negative pool to identify its differences in order to find similar objects in the image database.
|Fig 4. As in this case, the results can have large variations which may offer some unexpected inspiration.|
For this project, we have designed a web-application to allow users easy access. Significant objects like balustrades, capitals, arches and sculptures are mostly well recognized and found, however, several mistakes may occur due to distracting geometrical forms or clutter present in the images.
|Fig 5. The results show many variations of rusticated masonry and deliver a synoptic view of architectural form.|
The second task involves an interactive learning approach in which the user judges the search results or trains objects for search tasks individually. This approach helps to find similar parts either in a single architectural unit or in different buildings.
|Fig 6. Trained objects provide more accurate search results. In this case, all the capitals of the Berlin City Palace are included in the first two rows.|
|Fig 7. Processing pipeline: a) original image of size 400x500, b) binary edge image, c) subset of patches from binary edge image of size 21x21, d) self-similarity fire-pattern of Chamfer Matching costs for a small subset of patches, e) self-similarity cost matrix (size 1646x1646) between all patches, f) Region self-similarity: clustering of e) assigns patches to groups. Different groups are rendered in different color and the likelihood of a patch belonging to a group is visualized through saturation. .|
The third task is the analysis of architecture by self-similarity. Unlike the first approach, this task is supposed to be solved without any learned input. With the help of chamfer matching, the algorithm identifies the shapes inside the image and compares similar patches in other images to find matching regions. This approach should not only be able to recognize and show similar parts of buildings but also allow for a deeper understanding of their composition and design. There is some evidence that, in comparison to other picture databases, working with images of architecture is not as easy as had been previously assumed. The unsupervised approach is especially challenging for basic research.
|[ People | Publications | Research | Projects | Teaching | Student Projects | HCI Home | CompVis Home ]|
Last update: 21.04.2015, 14:56