Authors

Martin Evans

Document Type

Article

Abstract

Mark and recapture studies are a very popular method fisheries biologists use to assess certain fish populations in lakes. This process can be very labor intensive and expensive. Wild I.D. is free software developed by Dartmouth College that uses SIFT program to find unique features in photographs. Initially developed for identification of African land mammals the program gives each photo a score and percent match to other photos. Northern pike were used in this study to determine if the program can recognize simulated recapture events. Photos of sample fish were taken at two separate locations, the photos were then copied and cropped four different ways: Original Full, Original Middle, Negative Full, and Negative Middle. The program had a median percent match of 0.84, 0.85, 0.84, and 0.87, respectively. A KruskalWallis test was ran and a non-significant difference was found between the four sample groups (p-value = 0.90). For all 120 of our trials we found that the simulated recapture was the program’s top rated choice for being the best possible match. That gave the program a 100% success rating in choosing the recaptured fish. We are unaware if the software is able to identify a fish once the markings get distorted as the fish grows. Future studies will need to determine if there is any cause for concern about this possibility.

Publication Date

2015

Comments

Faculty sponsor: Dr. Andrew Hafs, Department of Biology, Aquatic Biology Program

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.