Facade users capture a photo of an interface they would like to use with a standard marker attached to it (we use a dollar bill). Using perspective transformation, the interface image is warped to the front view and absolute measurements are calculated. Then this image is sent to multiple crowd workers, who work in parallel to quickly label and describe elements of the interface. Blind users can then customize settings of the labeling strategy, and these labels and preferences are used to generate the 3D models of a tactile layer matching the original controls. Finally, an off-the-shelf 3D printer fabricates the layer, which is then attached to the interface using adhesives.