2006
DOI: 10.1007/11867586_60
|View full text |Cite
|
Sign up to set email alerts
|

Iterative 3-D Pose Correction and Content-Based Image Retrieval for Dorsal Fin Recognition

Abstract: Abstract.Contour or boundary descriptors may be used in contentbased image retrieval to effectively identify appropriate images when image content consists primarily of a single object of interest. The registration of object contours for the purposes of comparison is complicated when the objects of interest are characterized by open contours and when reliable feature points for contour alignment are absent. We present an application that employs an iterative approach to the alignment of open contours for the p… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

1
4
0
1

Year Published

2008
2008
2020
2020

Publication Types

Select...
5
4

Relationship

0
9

Authors

Journals

citations
Cited by 10 publications
(6 citation statements)
references
References 8 publications
1
4
0
1
Order By: Relevance
“…The relative accuracy, which was shown by Gamble et al (2008) to be constant with increasing catalogue size, was measured as the proportion of true matches that are ranked within the first 10% of the catalogue. Our program's relative accuracy was 77.5%, which is within the 50%-80% range achieved by other matching programs (Stewman et al, 2006;Finerty et al, 2007).…”
Section: Discussionsupporting
confidence: 72%
“…The relative accuracy, which was shown by Gamble et al (2008) to be constant with increasing catalogue size, was measured as the proportion of true matches that are ranked within the first 10% of the catalogue. Our program's relative accuracy was 77.5%, which is within the 50%-80% range achieved by other matching programs (Stewman et al, 2006;Finerty et al, 2007).…”
Section: Discussionsupporting
confidence: 72%
“…Würsig & Jefferson (1990). Photographs were analyzed and compared by at least two investigators using the Nikon View software and, more recently, Darwin (Stewman et al 2006). Catalogs were compared among areas to find matches of identified individuals, the main evidence of movement between two different locations.…”
Section: Methodsmentioning
confidence: 99%
“…Additionally, the proportion of the dorsal fin out of the water and the amount of water splash were also considered in the appropriate choice of photos (for more details, see Santos & 652 Victor Uber Paschoalini and Marcos César de Oliveira Santos Rosso, 2008). Darwin software was used to model photographs (see Stewman et al, 2006), and all matches were manually checked. Individual movements were analysed using estimated Euclidean distances within ArcGIS (ESRI, USA), following the shoreline whenever physical barriers such as islands were found in the middle of the path.…”
Section: Photo-identification Analysesmentioning
confidence: 99%