Fourier-based contour descriptors to relax positional standardization of the otolith images in AFORO queries
The otolith digital catalogue AFORO allows unknown otoliths to be classified automatically by using a comparison with its classified records. To do this, the otolith’s contour, which is extracted from an image, is used. In AFORO, otolith images follow a strict positional normalization. Only the left...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Consejo Superior de Investigaciones Científicas
2020-03-01
|
| Series: | Scientia Marina |
| Subjects: | |
| Online Access: | http://scientiamarina.revistas.csic.es/index.php/scientiamarina/article/view/1842 |
| _version_ | 1818717671225556992 |
|---|---|
| author | Pere Marti-Puig Amalia Manjabacas Antoni Lombarte |
| author_facet | Pere Marti-Puig Amalia Manjabacas Antoni Lombarte |
| author_sort | Pere Marti-Puig |
| collection | DOAJ |
| description | The otolith digital catalogue AFORO allows unknown otoliths to be classified automatically by using a comparison with its classified records. To do this, the otolith’s contour, which is extracted from an image, is used. In AFORO, otolith images follow a strict positional normalization. Only the left sagitta is considered, and the images must show the internal side of the whole otolith, with the sulcus acusticus visible, the dorsal side (D) placed in the dorsal position and the rostral side (R) placed on the right. The otolith in the incoming image to be classified must also follow the same positional normalization. Variations from the reference position worsen the classification results. In this article, robust contour descriptors are proposed to extend this functionality of AFORO to the images of otoliths that are poorly normalized, contain rotations, are entirely inverted or came from the right rather than the left sagitta. These descriptors are based on the discrete Fourier transform and could extend the classification functionality to incoming images that are taken and sent, for instance, from smartphones in a wide range of working conditions. |
| first_indexed | 2024-12-17T19:38:51Z |
| format | Article |
| id | doaj.art-a92d832b2d074b8da0e94b0b2c510d12 |
| institution | Directory Open Access Journal |
| issn | 0214-8358 1886-8134 |
| language | English |
| last_indexed | 2024-12-17T19:38:51Z |
| publishDate | 2020-03-01 |
| publisher | Consejo Superior de Investigaciones Científicas |
| record_format | Article |
| series | Scientia Marina |
| spelling | doaj.art-a92d832b2d074b8da0e94b0b2c510d122022-12-21T21:35:05ZengConsejo Superior de Investigaciones CientíficasScientia Marina0214-83581886-81342020-03-01841273710.3989/scimar.04961.15A1804Fourier-based contour descriptors to relax positional standardization of the otolith images in AFORO queriesPere Marti-Puig0https://orcid.org/0000-0001-6582-4551Amalia Manjabacas1https://orcid.org/0000-0001-8685-8697Antoni Lombarte2https://orcid.org/0000-0001-5215-4587Grup de Processament del Senyal. University of Vic (UVIC-UCC)Institut de Ciències del Mar, CSICInstitut de Ciències del Mar, CSICThe otolith digital catalogue AFORO allows unknown otoliths to be classified automatically by using a comparison with its classified records. To do this, the otolith’s contour, which is extracted from an image, is used. In AFORO, otolith images follow a strict positional normalization. Only the left sagitta is considered, and the images must show the internal side of the whole otolith, with the sulcus acusticus visible, the dorsal side (D) placed in the dorsal position and the rostral side (R) placed on the right. The otolith in the incoming image to be classified must also follow the same positional normalization. Variations from the reference position worsen the classification results. In this article, robust contour descriptors are proposed to extend this functionality of AFORO to the images of otoliths that are poorly normalized, contain rotations, are entirely inverted or came from the right rather than the left sagitta. These descriptors are based on the discrete Fourier transform and could extend the classification functionality to incoming images that are taken and sent, for instance, from smartphones in a wide range of working conditions.http://scientiamarina.revistas.csic.es/index.php/scientiamarina/article/view/1842otoliths2d shape descriptorscontour descriptorsrotation invariancefast fourier transforms |
| spellingShingle | Pere Marti-Puig Amalia Manjabacas Antoni Lombarte Fourier-based contour descriptors to relax positional standardization of the otolith images in AFORO queries Scientia Marina otoliths 2d shape descriptors contour descriptors rotation invariance fast fourier transforms |
| title | Fourier-based contour descriptors to relax positional standardization of the otolith images in AFORO queries |
| title_full | Fourier-based contour descriptors to relax positional standardization of the otolith images in AFORO queries |
| title_fullStr | Fourier-based contour descriptors to relax positional standardization of the otolith images in AFORO queries |
| title_full_unstemmed | Fourier-based contour descriptors to relax positional standardization of the otolith images in AFORO queries |
| title_short | Fourier-based contour descriptors to relax positional standardization of the otolith images in AFORO queries |
| title_sort | fourier based contour descriptors to relax positional standardization of the otolith images in aforo queries |
| topic | otoliths 2d shape descriptors contour descriptors rotation invariance fast fourier transforms |
| url | http://scientiamarina.revistas.csic.es/index.php/scientiamarina/article/view/1842 |
| work_keys_str_mv | AT peremartipuig fourierbasedcontourdescriptorstorelaxpositionalstandardizationoftheotolithimagesinaforoqueries AT amaliamanjabacas fourierbasedcontourdescriptorstorelaxpositionalstandardizationoftheotolithimagesinaforoqueries AT antonilombarte fourierbasedcontourdescriptorstorelaxpositionalstandardizationoftheotolithimagesinaforoqueries |