Enhanced methods for Saimaa ringed seal identification
Computer vision techniques have opened doors for practical, reliable and much safer methods for monitoring the animal populations in comparison with traditional methods. Old methods such as capturing the animals and installing sensors on their bodies are time consuming and may cause stress to the an...
Main Author: | |
---|---|
Other Authors: | |
Format: | Master Thesis |
Language: | English |
Published: |
2016
|
Subjects: | |
Online Access: | http://lutpub.lut.fi/handle/10024/125814 |
id |
ftlappeenranta:oai:lutpub.lut.fi:10024/125814 |
---|---|
record_format |
openpolar |
spelling |
ftlappeenranta:oai:lutpub.lut.fi:10024/125814 2023-05-15T18:07:07+02:00 Enhanced methods for Saimaa ringed seal identification Chehrsimin, Tina Lappeenrannan teknillinen yliopisto, School of Engineering Science, Laskennallinen tekniikka / Lappeenranta University of Technology, School of Engineering Science, Computational Engineering and Technical Physics 2016 59 fulltext http://lutpub.lut.fi/handle/10024/125814 en eng http://lutpub.lut.fi/handle/10024/125814 URN:NBN:fi-fe2016110327145 Saimaa ringed seals segmentation identification animal biometrics computer vision image processing Tekniikka / Technology Diplomityö Master's thesis 2016 ftlappeenranta 2021-12-30T14:11:56Z Computer vision techniques have opened doors for practical, reliable and much safer methods for monitoring the animal populations in comparison with traditional methods. Old methods such as capturing the animals and installing sensors on their bodies are time consuming and may cause stress to the animals and affect their behavior. In this study, an automatic image based identification algorithm to identify endangered Saimaa ringed seals is proposed. The identification algorithm consists of three main steps including image segmentation, image enhancement, and identification. The image segmentation method contains two steps: unsupervised segmentation and classification of the superpixels. The algorithm provides promising results by using a combination of different feature descriptors and classifiers. In the enhancement step, morphological operations, contrast enhancement, and color normalization are applied for segmented images to increase the performance. In the identification step, two algorithms were tested: Wild ID and Hot spotter. The identification algorithms were implemented on original images, segmented images and enhanced segmented images. The best results were obtained using Hot spotter tested with the enhanced segmented images. With a challenging data set used, 44% of the seals were correctly identified within the first match. Meanwhile, 66% of the cases, the correct seals were one of the 20 best matches. Master Thesis ringed seal LUTPub (LUT University) |
institution |
Open Polar |
collection |
LUTPub (LUT University) |
op_collection_id |
ftlappeenranta |
language |
English |
topic |
Saimaa ringed seals segmentation identification animal biometrics computer vision image processing Tekniikka / Technology |
spellingShingle |
Saimaa ringed seals segmentation identification animal biometrics computer vision image processing Tekniikka / Technology Chehrsimin, Tina Enhanced methods for Saimaa ringed seal identification |
topic_facet |
Saimaa ringed seals segmentation identification animal biometrics computer vision image processing Tekniikka / Technology |
description |
Computer vision techniques have opened doors for practical, reliable and much safer methods for monitoring the animal populations in comparison with traditional methods. Old methods such as capturing the animals and installing sensors on their bodies are time consuming and may cause stress to the animals and affect their behavior. In this study, an automatic image based identification algorithm to identify endangered Saimaa ringed seals is proposed. The identification algorithm consists of three main steps including image segmentation, image enhancement, and identification. The image segmentation method contains two steps: unsupervised segmentation and classification of the superpixels. The algorithm provides promising results by using a combination of different feature descriptors and classifiers. In the enhancement step, morphological operations, contrast enhancement, and color normalization are applied for segmented images to increase the performance. In the identification step, two algorithms were tested: Wild ID and Hot spotter. The identification algorithms were implemented on original images, segmented images and enhanced segmented images. The best results were obtained using Hot spotter tested with the enhanced segmented images. With a challenging data set used, 44% of the seals were correctly identified within the first match. Meanwhile, 66% of the cases, the correct seals were one of the 20 best matches. |
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 |
Chehrsimin, Tina |
author_facet |
Chehrsimin, Tina |
author_sort |
Chehrsimin, Tina |
title |
Enhanced methods for Saimaa ringed seal identification |
title_short |
Enhanced methods for Saimaa ringed seal identification |
title_full |
Enhanced methods for Saimaa ringed seal identification |
title_fullStr |
Enhanced methods for Saimaa ringed seal identification |
title_full_unstemmed |
Enhanced methods for Saimaa ringed seal identification |
title_sort |
enhanced methods for saimaa ringed seal identification |
publishDate |
2016 |
url |
http://lutpub.lut.fi/handle/10024/125814 |
genre |
ringed seal |
genre_facet |
ringed seal |
op_relation |
http://lutpub.lut.fi/handle/10024/125814 URN:NBN:fi-fe2016110327145 |
_version_ |
1766179025359732736 |