Automatic Detection of Features from Atlantic Salmon by Classical Image Processing
Master's thesis in Automation and signal Processing Master's thesis in Industrial economics The methods created for this project aim to locate the salmon in the image and extract features from it. The aim of the features are to recognize individual salmon from each other. Individual identi...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Master Thesis |
Language: | English |
Published: |
University of Stavanger, Norway
2019
|
Subjects: | |
Online Access: | http://hdl.handle.net/11250/2620307 |
id |
ftunivstavanger:oai:uis.brage.unit.no:11250/2620307 |
---|---|
record_format |
openpolar |
spelling |
ftunivstavanger:oai:uis.brage.unit.no:11250/2620307 2023-06-11T04:10:22+02:00 Automatic Detection of Features from Atlantic Salmon by Classical Image Processing Aanestad Lende, Christer Nising Lundal, Joachim Austvoll, Ivar 2019-06-14 application/pdf http://hdl.handle.net/11250/2620307 eng eng University of Stavanger, Norway Masteroppgave/UIS-TN-IDE/2019; http://hdl.handle.net/11250/2620307 Navngivelse 4.0 Internasjonal http://creativecommons.org/licenses/by/4.0/deed.no informasjonsteknologi industriell økonomi VDP::Social science: 200::Economics: 210 VDP::Technology: 500::Information and communication technology: 550 Master thesis 2019 ftunivstavanger 2023-05-29T16:02:59Z Master's thesis in Automation and signal Processing Master's thesis in Industrial economics The methods created for this project aim to locate the salmon in the image and extract features from it. The aim of the features are to recognize individual salmon from each other. Individual identification, done by RFID today, is important in the Norwegian aquaculture industry, mostly for scientific purposes. If this could be implemented by machine vision instead, it could be expanded to commercial purposes and tracking of larger masses, which could be economically beneficial for the industry. Based on reasonable assumptions, some economic scenarios were computed to estimate potential savings that could be achieved by successful implementation of such a system. Based on the assumptions, it is reasonable to believe that this could save roughly 5,04 MNOK every year per offshore fish cage applied to. The potential costs are however somewhat uncertain. K-means clustering was used to extract the salmon from the image. This was successful for all images. It should be noted that the data-set was cleaned of images which did not meet certain requirements. A method was developed to detect the nose and tail tips of the salmon mainly to estimate its orientation. It worked on all images largely due to the successful cropping done by the k-means clustering. Another method was created to detect the pectoral fin on the salmon, using segmentation by thresholding, as well as structural measures and area-thresholds. It achieved a best success rate at 99.2% on 537 images from one data-set(main set) and at worst a success rate of 93.5% on 246 images from another data-set(second set). It was important to detect the gill-opening on the salmon, which would lead to extract a ROI around the head. The method for locating the gill-opening therefore had an important task in detecting the back of the gills, towards the body, such that the area of the head was not cropped too small. The method had an average of detecting 5.32 pixels away from the ... Master Thesis Atlantic salmon University of Stavanger: UiS Brage |
institution |
Open Polar |
collection |
University of Stavanger: UiS Brage |
op_collection_id |
ftunivstavanger |
language |
English |
topic |
informasjonsteknologi industriell økonomi VDP::Social science: 200::Economics: 210 VDP::Technology: 500::Information and communication technology: 550 |
spellingShingle |
informasjonsteknologi industriell økonomi VDP::Social science: 200::Economics: 210 VDP::Technology: 500::Information and communication technology: 550 Aanestad Lende, Christer Nising Lundal, Joachim Automatic Detection of Features from Atlantic Salmon by Classical Image Processing |
topic_facet |
informasjonsteknologi industriell økonomi VDP::Social science: 200::Economics: 210 VDP::Technology: 500::Information and communication technology: 550 |
description |
Master's thesis in Automation and signal Processing Master's thesis in Industrial economics The methods created for this project aim to locate the salmon in the image and extract features from it. The aim of the features are to recognize individual salmon from each other. Individual identification, done by RFID today, is important in the Norwegian aquaculture industry, mostly for scientific purposes. If this could be implemented by machine vision instead, it could be expanded to commercial purposes and tracking of larger masses, which could be economically beneficial for the industry. Based on reasonable assumptions, some economic scenarios were computed to estimate potential savings that could be achieved by successful implementation of such a system. Based on the assumptions, it is reasonable to believe that this could save roughly 5,04 MNOK every year per offshore fish cage applied to. The potential costs are however somewhat uncertain. K-means clustering was used to extract the salmon from the image. This was successful for all images. It should be noted that the data-set was cleaned of images which did not meet certain requirements. A method was developed to detect the nose and tail tips of the salmon mainly to estimate its orientation. It worked on all images largely due to the successful cropping done by the k-means clustering. Another method was created to detect the pectoral fin on the salmon, using segmentation by thresholding, as well as structural measures and area-thresholds. It achieved a best success rate at 99.2% on 537 images from one data-set(main set) and at worst a success rate of 93.5% on 246 images from another data-set(second set). It was important to detect the gill-opening on the salmon, which would lead to extract a ROI around the head. The method for locating the gill-opening therefore had an important task in detecting the back of the gills, towards the body, such that the area of the head was not cropped too small. The method had an average of detecting 5.32 pixels away from the ... |
author2 |
Austvoll, Ivar |
format |
Master Thesis |
author |
Aanestad Lende, Christer Nising Lundal, Joachim |
author_facet |
Aanestad Lende, Christer Nising Lundal, Joachim |
author_sort |
Aanestad Lende, Christer |
title |
Automatic Detection of Features from Atlantic Salmon by Classical Image Processing |
title_short |
Automatic Detection of Features from Atlantic Salmon by Classical Image Processing |
title_full |
Automatic Detection of Features from Atlantic Salmon by Classical Image Processing |
title_fullStr |
Automatic Detection of Features from Atlantic Salmon by Classical Image Processing |
title_full_unstemmed |
Automatic Detection of Features from Atlantic Salmon by Classical Image Processing |
title_sort |
automatic detection of features from atlantic salmon by classical image processing |
publisher |
University of Stavanger, Norway |
publishDate |
2019 |
url |
http://hdl.handle.net/11250/2620307 |
genre |
Atlantic salmon |
genre_facet |
Atlantic salmon |
op_relation |
Masteroppgave/UIS-TN-IDE/2019; http://hdl.handle.net/11250/2620307 |
op_rights |
Navngivelse 4.0 Internasjonal http://creativecommons.org/licenses/by/4.0/deed.no |
_version_ |
1768384724462469120 |