Resource Summary Report  New Search Previous Search Results

URL: https://dx.doi.org/DOI:10.17504/protocols.io.be2rjgd6

Authors: Rosa I Ramos-Arredondo, Blanca E, Diane Gendron, J. Francisco Gallegos-Funes, Dante Mújica-Vargas, J.B. Rosas-Fernández

Summary: Photoidentification is a method used by biologists to classify animals primarily to track endangered species. Different methods of identification, either manual or computational, have been developed since the 1990s, which until now have remained in use. However, these methods can introduce a factor of subjectivity when classifying an individual animal, creating uncertainty or inaccuracy in the results obtained as a result of the human criteria involved. For this reason, one of the main objectives in photoidentification is to implement an automated mechanism that is free of biases, is portable, and is easily used. The main aim of this work is to develop an autonomous and portable photoidentification system through the optimization of image classification algorithms that have high statistical dependence, with the goal of classifying images of the dorsal fin of the blue whale through offline information processing on a mobile device. The new proposed methodology is based on the Scale Invariant Feature Transform (SIFT) that, in conjunction with statistical discriminators such as the variance and the standard deviation, fits the extracted data and selects the closest pixels that make up the edges of the dorsal fin of the blue whale. In this way, we ensure the elimination of the most common external factors that could affect the quality of the image, thus avoiding the elimination of relevant sections of the dorsal fin. The blue whale photoidentification method presented in this work has been developed at the Instituto Politécnico Nacional on the coast of Baja California Sur. The results shown have been validated qualitatively and quantitatively in terms of sensitivity, specificity and accuracy on the Jetson Tegra TK1 mobile platform. The presented solution balances the results obtained with the computational cost of the execution of the algorithm, and yields a portable system that could be beneficial for field studies.

Associated Publications: Ramos-Arredondo RI, Carvajal-Gámez BE, Gendron D, Gallegos-Funes FJ, Mújica-Vargas D, Rosas-Fernández JB (2020) PhotoId-Whale: Blue whale dorsal fin classification for mobile devices. PLoS ONE 15(10): e0237570. doi: 10.1371/journal.pone.0237570

Affiliations: Instituto Politécnico Nacional - ESIME Culhuacan , Blanca E. Carvajal-Gámez(SEPI-ESCOM, Instituto Politécnico Nacional), (CICIMAR, Instituto Politécnico Nacional), (SEPI-Zacatenco, Instituto Politécnico Nacional), (Departamento de Ciencias Computacionales, Tecnológico Nacional de México), (Secretaría de Educación, Ciencia, Tecnología e Innovación)

External URL: https://doi.org/10.1371/journal.pone.0237570

Version: 1

Publication Date: 2020

Expand All Collapse