| Author(s): |
Homsi Goulart, Antonio Jose
;
Morimitsu, Alexandre
;
Jacomassi, Renan
;
Hirata, Nina
;
Lopes, Rubens
;
IEEE
Total Authors: 6
|
| Document type: | Journal article |
| Source: | OCEANS 2021: SAN DIEGO - PORTO; v. N/A, p. 4-pg., 2021-01-01. |
| Abstract | |
In this paper we present a pipeline to cluster unlabelled image samples. Although not restricted to plankton image applications, we present the system within this context. Feature maps obtained from a deep learning architecture (DenseNet) are fed to the t-SNE projection in order to obtain 2D clusters. The method successfully creates clusters that can be used in interactive software, for quick manual classification of images batches. (AU) | |
| FAPESP's process: | 21/02902-8 - Computational technical support for the project World Wide Web of Plankton Image Curation (WWW.PIC) |
| Grantee: | Alexandre Morimitsu |
| Support Opportunities: | Scholarships in Brazil - Technical Training Program - Technical Training |
| FAPESP's process: | 20/15170-2 - Data efficient methods for plankton image classification |
| Grantee: | Antonio Jose Homsi Goulart |
| Support Opportunities: | Scholarships in Brazil - Post-Doctoral |