Welcome to the InfoSci Platform
Reference Hub2
Automatic Fish Segmentation and Recognition for Trawl-Based Cameras

Automatic Fish Segmentation and Recognition for Trawl-Based Cameras

Meng-Che Chuang, Jenq-Neng Hwang, Kresimir Williams
Copyright: © 2016 |Pages: 28
ISBN13: 9781466694354|ISBN10: 1466694351|EISBN13: 9781466694361
DOI: 10.4018/978-1-4666-9435-4.ch005
Cite Chapter Cite Chapter

MLA

Chuang, Meng-Che, et al. "Automatic Fish Segmentation and Recognition for Trawl-Based Cameras." Computer Vision and Pattern Recognition in Environmental Informatics, edited by Jun Zhou, et al., IGI Global, 2016, pp. 79-106. https://doi.org/10.4018/978-1-4666-9435-4.ch005

APA

Chuang, M., Hwang, J., & Williams, K. (2016). Automatic Fish Segmentation and Recognition for Trawl-Based Cameras. In J. Zhou, X. Bai, & T. Caelli (Eds.), Computer Vision and Pattern Recognition in Environmental Informatics (pp. 79-106). IGI Global. https://doi.org/10.4018/978-1-4666-9435-4.ch005

Chicago

Chuang, Meng-Che, Jenq-Neng Hwang, and Kresimir Williams. "Automatic Fish Segmentation and Recognition for Trawl-Based Cameras." In Computer Vision and Pattern Recognition in Environmental Informatics, edited by Jun Zhou, Xiao Bai, and Terry Caelli, 79-106. Hershey, PA: IGI Global, 2016. https://doi.org/10.4018/978-1-4666-9435-4.ch005

Export Reference

Mendeley
Favorite

Abstract

Camera-based fish abundance estimation with the aid of visual analysis techniques has drawn increasing attention. Live fish segmentation and recognition in open aquatic habitats, however, suffers from fast light attenuation, ubiquitous noise and non-lateral views of fish. In this chapter, an automatic live fish segmentation and recognition framework for trawl-based cameras is proposed. To mitigate the illumination issues, double local thresholding method is integrated with histogram backprojection to produce an accurate shape of fish segmentation. For recognition, a hierarchical partial classification is learned so that the coarse-to-fine categorization stops at any level where ambiguity exists. Attributes from important fish anatomical parts are focused to generate discriminative feature descriptors. Experiments on mid-water image sets show that the proposed framework achieves up to 93% of accuracy on live fish recognition based on automatic and robust segmentation results.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.