A bioinformatics approach to 2D shape classification

In the past, the huge and profitable interaction between Pattern Recognition and biology/bioinformatics was mainly unidirectional, namely targeted at applying PR tools and ideas to analyse biological data. In this paper we investigate an alternative approach, which exploits bioinformatics solutions to solve PR problems: in particular, we address the 2D shape classification problem using classical biological sequence analysis approaches - for which a vast amount of tools and solutions have been developed and improved in more than 40 years of research. First, we highlight the similarities between 2D shapes and biological sequences, then we propose three methods to encode a shape as a biological sequence. Given the encoding, we can employ standard biological sequence analysis tools to derive a similarity, which can be exploited in a nearest neighbor framework. Classification results, obtained on 5 standard datasets, confirm the potentials of the proposed unconventional interaction between PR and bioinformatics. Moreover, we provide some evidences of how it is possible to exploit other bioinformatics concepts and tools to interpret data and results, confirming the flexibility of the proposed framework.