New similarity scale to recognize bird calls and abnormal sounds of concrete/machine

Development of pattern matching software using multi-CPU

Abstract

A new similarity scale called the Geometric Distance, that numerically evaluates the degree of likeness between the standard pattern and the input pattern is proposed. Traditionally, the similarity scales known as the Euclidean distance and cosine similarity have been widely used to measure likeness. Traditional methods do not perform well in the presence of noise or pattern distortions. In this paper, a mathematical model for similarity is proposed to overcome these limitations of the earlier models, and a new algorithm based on a one-to-many point mapping is proposed to realize the mathematical model. Using the new similarity scale, experiments in bird call recognition were carried out in noisy environments. Furthermore, experiments in abnormal sound recognition of concrete structure were carried out. In all cases a significant improvement in recognition accuracy is demonstrated.