AUTOMATED RECOGNITION SYSTEM FOR MUSICAL SCORE - THE VISION SYSTEM OF WABOT-2.

This paper reports on WABOT-2 vision system, which can recognize not only commercially available printed musical scores but also instant lettering scores in real time, using an extraction algorithm based on the musical score structure with special hardware and knowledge-base music comprehension software. Several automated recognition systems for printed music have been reported. However, none of these systems are suitable for use as vision for music playing robots, where real time recognition is required under an extremely poor data environment where a video camera is placed in the robot's head and music sheets are often curved or otherwise deformed on the music stand. In order to directly convey the vision system output to the robot hands, contradictions and inharmonic codes in the pattern discrimination results are checked, using knowledge-base music notation. The resulting music robot vision performance is able to recognize, one sheet of commercially available printed of nursery song music for an electric piano, having up to three parts in 15 seconds, with approximately 100% accuracy.