HISI: A soft framework for building recognition

In an effort to develop an interaction mechanism based on visual sensing to trigger and improve delivery of context based services and information pertinent to location in a solicited and near real time manner, we present in this paper HISI, a soft recognition approach to the processing and identification of buildings. Using a coarse joint histogram technique, an image captured by a mobile user with a cell phone is pre-processed to reduce the search space to an adaptive list of potential buildings, after which a weighted fusion of different SIFT maps identifies the building in question. Experimental results showed HISI´s effectiveness with respect to other published results in the literature and motivates further extensions to HISI, as it carries expectations for commercial values to the delivery of context based services initiated by users.