next up previous


Proceeding of International Conference
Kaoru Kimura, Felicia Misamanana Rabarison, Kawanaka Kohei, Hiroki Tanioka, Tetsushi Ueta, Animal Stamp Rally Application using Image Recognition, IIAI, The 7th International Conference on Smart Computing and Artificial Intelligence (SCAI 2019), 1077-1078, Toyama, July 2019.
Abstract: Tokushima zoo is a municipal zoo housing a lot ofanimals for educational purpose. Thus, Tokushima city wantsvisitors to observe animals as many as possible whilst havingfun. The animal stamp rally is a game that visitors collect aseries of stamps at around animals which visitors have observed.Not to provide real stamps, tables and stamp cards, we developan animal stamp rally application. Thanks to the ConvolutionalNeural Network (CNN), the application can recognize stampsfrom snapshots of real animals instead of real stamps or QRcodes. Additionally, to improve animal recognition accuracy, theapplication uses GPS information. In this paper, we describesa progress of our development of the animal stamp rallyapplication, and estimates its recognition accuracy.


Contact address: ueta @ tokushima-u.ac.jp
2020-10-01