Fully automatic segmentation of bee wing images

Authors

DOI:

https://doi.org/10.5335/rbca.v12i2.10420

Keywords:

image pre-processing, image processing, image segmentation, edge detection, venation classification

Abstract

Bee preservation is important because approximately 70% of all pollination of food crops is made by them and this service costs more than $ 65 billion annually. In order to help this preservation, the identification of the bee species is necessary, and since this is a costly and time-consuming process, techniques that automate and facilitate this identification become relevant. Images of bees' wings in conjunction with computer vision and artificial intelligence techniques can be used to automate this process. This paper presents an approach to do segmentation of bees' wing images and feature extraction. Our approach was evaluated using the modified Hausdorff distance and F measure. The results were, at least, 24% more precise than the related approaches and the proposed approach was able to deal with noisy images.

Downloads

Download data is not yet available.

Author Biographies

  • João Marcos Garcia Fagundes, University of Sao Paulo

    Undergraduate student in Information Systems at the University of São Paulo.

  • Allan Rodrigues Rebelo, University of Sao Paulo

    Master student in Information Systems at the University of São Paulo.

  • Luciano Antonio Digiampietri, University of Sao Paulo

    Associate Professor at University of Sao Paulo (USP). Luciano has an ungraduate degree in Computer Science from Universidade Estadual de Campinas (2002) and is Ph.D. in Computer Science from Universidade Estadual de Campinas (2007). He has experience in Computer Science, focusing on Database, Computational Biology and Artificial Intelligence, acting on the following subjects: bioinformatics, web services, bacterial genome, workflow and social network analysis.

  • Helton Hideraldo Bíscaro, University of Sao Paulo

    Graduation at Matemática from Universidade Estadual Paulista Júlio de Mesquita Filho (1998), master's at Computer Science from Universidade de São Paulo (2001) and doctorate at Computer Science from Universidade de São Paulo (2005). Has experience in Computer Science, focusing on Analytical Models and of Simulation, acting on the following subjects: surface reconstruction, estrutura de dados, visualização, nuvem de pontos and samples points.

Downloads

Published

2020-06-02

Issue

Section

Original Paper

How to Cite

[1]
2020. Fully automatic segmentation of bee wing images. Brazilian Journal of Applied Computing. 12, 2 (Jun. 2020), 37–45. DOI:https://doi.org/10.5335/rbca.v12i2.10420.