Saimaa ringed seal fur pattern extraction for identification purposes
The Saimaa ringed seal is considered to be endangered and is facing a very high risk of extinction. he conservation efforts largely depend on the ability to track and monitor each individual seal. Photo-identification using camera traps has been successfully used for wildlife monitoring. Each seal h...
Main Author: | |
---|---|
Other Authors: | |
Format: | Master Thesis |
Language: | English |
Published: |
2017
|
Subjects: | |
Online Access: | http://lutpub.lut.fi/handle/10024/135303 |
id |
ftlappeenranta:oai:lutpub.lut.fi:10024/135303 |
---|---|
record_format |
openpolar |
spelling |
ftlappeenranta:oai:lutpub.lut.fi:10024/135303 2023-05-15T18:07:06+02:00 Saimaa ringed seal fur pattern extraction for identification purposes Nepovinnykh, Ekaterina Lappeenrannan teknillinen yliopisto, School of Engineering Science, Laskennallinen tekniikka / Lappeenranta University of Technology, School of Engineering Science, Computational Engineering and Technical Physics 2017 49 fulltext http://lutpub.lut.fi/handle/10024/135303 en eng http://lutpub.lut.fi/handle/10024/135303 URN:NBN:fi-fe201705236829 Saimaa ringed seals identification animal biometrics computer vision image processing convolutional neural network Datatiede / Data science Diplomityö Master's thesis 2017 ftlappeenranta 2021-12-30T14:12:05Z The Saimaa ringed seal is considered to be endangered and is facing a very high risk of extinction. he conservation efforts largely depend on the ability to track and monitor each individual seal. Photo-identification using camera traps has been successfully used for wildlife monitoring. Each seal has a unique fur pattern that a human expert can match to a specific seal labeled earlier. This thesis focuses on automatic identification of Saimaa ringed seals based on fur pattern extraction. This consists of segmentation of an image with the goal of extracting the seal, extraction of fur pattern from the segmented seal image and searching for the same seal in the seal database. Two methods of Saimaa ringed seal identification based on transfer learning are proposed in this work. The first method involves re-training of the existing convolutional neural network (CNN). The second method involves using the existing CNN trained for image classification as a means to extract features from seal images which are then used to train a Support Vector Machine (SVM) classifier. Both methods are implemented, tested and compared. Both approaches show good results with total accuracy of 91.2% for CNN and 90.5% for SVM. Master Thesis ringed seal LUTPub (LUT University) |
institution |
Open Polar |
collection |
LUTPub (LUT University) |
op_collection_id |
ftlappeenranta |
language |
English |
topic |
Saimaa ringed seals identification animal biometrics computer vision image processing convolutional neural network Datatiede / Data science |
spellingShingle |
Saimaa ringed seals identification animal biometrics computer vision image processing convolutional neural network Datatiede / Data science Nepovinnykh, Ekaterina Saimaa ringed seal fur pattern extraction for identification purposes |
topic_facet |
Saimaa ringed seals identification animal biometrics computer vision image processing convolutional neural network Datatiede / Data science |
description |
The Saimaa ringed seal is considered to be endangered and is facing a very high risk of extinction. he conservation efforts largely depend on the ability to track and monitor each individual seal. Photo-identification using camera traps has been successfully used for wildlife monitoring. Each seal has a unique fur pattern that a human expert can match to a specific seal labeled earlier. This thesis focuses on automatic identification of Saimaa ringed seals based on fur pattern extraction. This consists of segmentation of an image with the goal of extracting the seal, extraction of fur pattern from the segmented seal image and searching for the same seal in the seal database. Two methods of Saimaa ringed seal identification based on transfer learning are proposed in this work. The first method involves re-training of the existing convolutional neural network (CNN). The second method involves using the existing CNN trained for image classification as a means to extract features from seal images which are then used to train a Support Vector Machine (SVM) classifier. Both methods are implemented, tested and compared. Both approaches show good results with total accuracy of 91.2% for CNN and 90.5% for SVM. |
author2 |
Lappeenrannan teknillinen yliopisto, School of Engineering Science, Laskennallinen tekniikka / Lappeenranta University of Technology, School of Engineering Science, Computational Engineering and Technical Physics |
format |
Master Thesis |
author |
Nepovinnykh, Ekaterina |
author_facet |
Nepovinnykh, Ekaterina |
author_sort |
Nepovinnykh, Ekaterina |
title |
Saimaa ringed seal fur pattern extraction for identification purposes |
title_short |
Saimaa ringed seal fur pattern extraction for identification purposes |
title_full |
Saimaa ringed seal fur pattern extraction for identification purposes |
title_fullStr |
Saimaa ringed seal fur pattern extraction for identification purposes |
title_full_unstemmed |
Saimaa ringed seal fur pattern extraction for identification purposes |
title_sort |
saimaa ringed seal fur pattern extraction for identification purposes |
publishDate |
2017 |
url |
http://lutpub.lut.fi/handle/10024/135303 |
genre |
ringed seal |
genre_facet |
ringed seal |
op_relation |
http://lutpub.lut.fi/handle/10024/135303 URN:NBN:fi-fe201705236829 |
_version_ |
1766179017677864960 |