From Windows to Logos: Analyzing Outdoor Images to Aid Flyer Classification

Payam Pourashraf, Noriko Tomuro, Saeed Bagheri Shouraki

Abstract: The goal of this paper was to create a new method for analyzing the online real estate flyers based on their property types. We created an algorithm which identifies the buildings and windows from the buildings in order to extract some useful features for classifying the flyers. Our novel approach for building recognition has two main steps: 1- Building Detector 2- Region Growing. Our novel window detection algorithm uses vanishing point to identify nearly the best angle for applying window detection. It transforms the 2D image into 3D and rotates the 3D image around the z-axis and picks the appropriate angle based on the vanishing points. Using these two novel techniques we were be able to extract a new feature vector which is used to build our final model. This final model is able to classify Retail spaces very well based on the Window and logo features.