Improvement of an Interactive Media System "RAKUGACKY"
Satomi Kato, Shinji Mizuno · 2016
“RAKUGACKY” is an interactive media system that could generate sounds from a hand-drawn sketch. It is necessary to analyze a sketch to generate sounds suitable for the sketch. The former system used colors and simple shape feature values of objects in a sketch such a circularity and an area, to recognize each object. Thus the system could recognize only simple objects in a sketch. In this paper, we improve our system to use more complex features of objects and recognize complex objects in a sketch by extracting and learning features of complex objects in a machine learning method. For example, the improved method could analyze hand-drawn animals such as cat, dog and sheep, and could synthesize cries of each animal interactively.