Use this url to cite publication: https://hdl.handle.net/20.500.14172/5763
Options
Automatic benthic imagery recognition using a hierarchical two-stage approach
Type of publication
Straipsnis Web of Science ir Scopus duomenų bazėje / Article in Web of Science and Scopus database (S1)
Type of document
type::text::journal::journal article::research article
Author(s)
Rimavičius, Tadas | Kauno technologijos universitetas | |
Gelžinis, Adas | Kauno technologijos universitetas | |
Verikas, Antanas | Kauno technologijos universitetas | Halmstad University |
Vaičiukynas, Evaldas | Kauno technologijos universitetas | |
Bačauskienė, Marija | Kauno technologijos universitetas | |
Title
Automatic benthic imagery recognition using a hierarchical two-stage approach
Publisher (trusted)
„Springer“ grupė |
Date Issued
Date Issued |
---|
2018 |
Extent
p. 1107-1114
Is part of
Signal, image and video processing. London : Springer, 2018, vol. 12, iss. 6.
Abstract
The main objective of this work is to establish an automated classification system of seabed images. A novel two-stage approach to solving the image region classification task is presented. The first stage is based on information characterizing geometry, colour and texture of the region being analysed. Random forests and support vector machines are considered as classifiers in this work. In the second stage, additional information characterizing image regions surrounding the region being analysed is used. The reliability of decisions made in the first stage regarding the surrounding regions is taken into account when constructing a feature vector for the second stage. The proposed techniquewas tested in an image region recognition task including five benthic classes: red algae, sponge, sand, lithothamnium and kelp. The taskwas solved with the average accuracy of 90.11% using a data set consisting of 4589 image regions and the tenfold cross-validation to assess the performance. The two-stage approach allowed increasing the classification accuracy for all the five classes, more than 27% for the “difficult” to recognize “kelp” class.
Is Referenced by
ISSN (of the container)
1863-1703
1863-1711
WOS
000441392700011
Scopus
2-s2.0-85051420102
eLABa
30381402
Coverage Spatial
Jungtinė Karalystė / United Kingdom of Great Britain and Northern Ireland (GB)
Language
Anglų / English (en)
Bibliographic Details
28
Affiliation(s)
Access Rights
Apribota prieiga / Restricted Access
File(s)
Journal | IF | AIF | AIF (min) | AIF (max) | Cat | AV | Year | Quartile |
---|---|---|---|---|---|---|---|---|
Signal Image and Video Processing | 1.894 | 3.522 | 3.195 | 3.85 | 2 | 0.583 | 2018 | Q3 |
Journal | IF | AIF | AIF (min) | AIF (max) | Cat | AV | Year | Quartile |
---|---|---|---|---|---|---|---|---|
Signal Image and Video Processing | 1.894 | 3.522 | 3.195 | 3.85 | 2 | 0.583 | 2018 | Q3 |
Journal | Cite Score | SNIP | SJR | Year | Quartile |
---|---|---|---|---|---|
Signal, Image and Video Processing | 3.7 | 1.269 | 0.501 | 2018 | Q2 |