[2C3-OS-17] [Organized Session] OS-17

[2C3-OS-17-05] Classification of Real Estate Images using Bottleneck Features

〇Suguru Toyohara¹, Youiti Kado², Toshihiko Yamasaki³, Susumu Fujimori¹, Ikuo Tahara¹ (1. Tokyo University of Science, 2. At Home Co., Ltd., 3. The University of Tokyo)

Keywords:Real Estate Technology, Image Classification, Deep Learning

Image processing enhanced by deep learning is now being actively applied to real-world issues. The real estate industry, which owns lots of property information, also expects to develop new services using deep learning. In this paper, we present the classification methods for property images using bottleneck features generated by convolution networks (CNN), and experimentally show that we can achieve 88% accuracy in Top-1.