Photo Identification of Chinook Salmon
CSEF · 2014 Mathematics & Software
Overview
Objectives/Goals The purpose is to use spot pattern recognition procedures and image processing to identify individual Chinook salmon using a program called Stripespotter. We must first test the accuracy of the program by comparing photos of different Chinook salmon by categorizing them in a specific ranking order. Methods/Materials Two buckets, anesthesia, camera, Styrofoam board, Photo Elements, Stripespotter I removed three salmon from 15 tanks and placed them in a bucket, shortly before adding a few drops of anesthesia. I placed a label next to each fish that indicated which fish it was and the tank number it was in. After completing the 15 tanks, I repeated the process, while labeling each tank number with a letter B. With the 90 different photos of Chinook salmon, I extracted a portion of the spots from each fish using Photo Elements, and then entered the revised pictures into Stripespotter, which ranked these photos according to the "likeness" of the main photo that I selected. Results Ninety of the 90 photos listed as rank 1, while 22 of the 90 photos, or 24.4%, listed as rank 2, indicating a "complete accuracy." After examining further results, there was a steady decrease in the number of identifiable pictures as the rank number continued to increase until it reached rank 10. According to my data, 50 of the 90 photos, or 55.6%, were ranked within the first ten rankings, indicating a "partial accuracy." Conclusions/Discussion To some degree, Stripespotter is an accurate program; however, workers at hacheries shouldn't solely rely on a program that doesn't rank every original photo as rank 1 and every secondary photo as rank 2; again, it depends on that perception of "accuracy." Possible errors may have occurred in this eperiment such as fish movement or light quality, so before characterizing Stripespotter as an inaccurate program, we must first improve image processing.
Summary statement
The purpose is the test the accuracy of a coding program called Stripespotter to determine if identifying Chinook salmon through photo recognition is a more effective way of tracking fish.
Help received
Used equipment from the Merced River Fish Facility under supervisor Mr. Adelizi, received physical help e.g. lifting buckets, photographer took pictures
Competition history
- CSEF 2014
Resources
Related projects
CSEF · 2010
Salmonids by Numbers II: A Predictive Simulation-Analysis of San Lorenzo River Fish Populations
CSEF · 2011
Population Modeling of the Sacramento Salmon: Combining Compositional Data with Traditional Abundance Estimates
CSEF · 2004
Migratory Magnetism
ISEF · 2017
Mathematical Analysis of Melanocyte Patterns on Danio rerio
CSEF · 2008
Something Smells Fishy! The Study of Molly Fish, in Relation to the Chemical Migratory Phenomenon of Alaskan Salmon
CSEF · 2015
A Computer Program to Track and Count Particle Trails
ISEF · 2016
Formulating Different Detection Algorithms to Identify Invasive Red Lionfish in South Florida and the Bahamas
CSEF · 2006
Water Temperature: Does It Affect Salmonid Growth?
Closest projects by meaning, across every fair and year in the corpus.
Browse more like this
Source: California Science & Engineering Fair public projects