Abstract
A neural network for recognition of handwritten musical notes, based on the well-known Neocognitron model, is described. The Neocognitron has been used for the “what” pathway (symbol recognition), while contextual knowledge has been applied for the “where” (symbol placement). This way, we benefit from dividing the process for dealing with this complicated recognition task. Also, different degrees of intrusiveness in “learning” have been incorporated in the same network: More intrusive supervised learning has been implemented in the lower neuron layers and less intrusive in the upper one. This way, the network adapts itself to the handwriting of the user. The network consists of a 13×49 input layer and three pairs of “simple” and “complex” neuron layers. It has been trained to recognize 20 symbols of unconnected notes on a musical staff and was tested with a set of unlearned input notes. Its recognition rate for the individual unseen notes was up to 93%, averaging 80% for all categories. These preliminary results indicate that a modified Neocognitron could be a good candidate for identification of handwritten musical notes.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Biostein D, Baird HS (1992) A critical survey of music image analysis. In: Baird H, Bunke H, and Yamamoto K (eds) Structured document image analysis. Springer, Berlin Heidelberg New York, pp 405–434
Bulis A, Almog R, Gerner M, Shimony U (1992) Computerized recognition of handwritten musical notes. Proceedings of the International Computer Music Conference ICMC-92, San Jose, Calif, pp 110–112
Carpenter GA (1989) Neural network models for pattern recognition and associative memory. Neural Networks 2:243–257
Eun Jin K, Yillbyung L (1991) Handwritten hangul recognition using a modified neocognitron. Neural Networks 4:743–750.
Fujinaga I (1992) Optical music recognition system which learns. SPIE 1785:210–217
Fukushima K (1987) Neural network model for selective attention in visual pattern recognition and associative recall. Appl Opt 26:4985–4992
Fukushima K (1988) Neocognitron: a hierarchical neural network capable of visual pattern recognition. Neural Networks 1:119–130
Fukushima K (1989) Neocognitron: a hierarchical neural network capable of visual pattern recognition. Neural Networks 2:413–420
Fukushima K, Miyake S (1982) Neocognitron: a new algorithm for pattern recognition tolerant of deformations and shifts in position. Pattern Recogn 15:455–469
Fukushima K, Miyake S, Ito T (1983) Neocognitron: a neural network model for a mechanism of visual pattern recognition. IEEE Trans Syst Man Cybern 13:826–834
Hewlett WB, Selfridge-Field E (1994) Optical recognition of musical notation. Comput Musicol 9:109–166
Lippman RP (1987) An introduction to computing with neural nets. IEEE Acoust Speech Signal Process Mag 4:4–22
Martin P, Bellissant C (1992) Neural networks for the recognition of engraved musical scores. Int J Pattern Recogn Artif Intell 6:193–208
Modayur BR, Visvanathan R, Haralick RM, Shapiro LG (1993) MUSER: a prototype musical score recognition system using mathematical morphology. Machine Vision Appl 6:140–150
Roach JW, Tatern JE (1988) Using domain knowledge in low-level visual processing to interpert handwritten music: an experiment. Pattern Recogn 21:33–44
Sanchez-Sinencio E, Lau C (1992) Artificial neural networks. IEEE Press, New York
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Yadid-Pecht, O., Gerner, M., Dvir, L. et al. Recognition of handwritten musical notes by a modified Neocognitron. Machine Vis. Apps. 9, 65–72 (1996). https://doi.org/10.1007/BF01214361
Issue Date:
DOI: https://doi.org/10.1007/BF01214361