Applying transfer learning for marine animal image classification using pre-trained convolutional neural network [thesis] / Alexander S. Alejado. Ellaine T. Gabotero, and Naomi P. Ezaki.
Material type:
TextPublication details: Dumaguete City : Foundation University, 2019.Description: v, 53 leaves : ill. (col.) 275 cmSubject(s): LOC classification: - LG 221 D35 C66 A5 C66 .2019 Al252
| Item type | Current library | Call number | Status | Barcode | |
|---|---|---|---|---|---|
Thesis
|
Foundationiana Section, University Records and Archives Center (URAC) Undergraduate Thesis | LG 221 D35 C66 A5 C66 2019 Al252 (Browse shelf(Opens below)) | Available | 0132024005004 |
Browsing University Records and Archives Center (URAC) shelves, Shelving location: Undergraduate Thesis Close shelf browser (Hides shelf browser)
| No cover image available | No cover image available | No cover image available | No cover image available | No cover image available | No cover image available | No cover image available | ||
| LG 221 D35 C66 A5 C66 2013 C1148 Robotic soil surface moisture detection system [thesis] / | LG 221 D35 C66 A5 C66 2016 P6553 Polar [thesis] : a logistic machine using intel galileo and android app / | LG 221 D35 C66 A5 C66 2017 V366 Drone stabilization system based on kalman and proportional-integral-derivative algorithms [thesis] / | LG 221 D35 C66 A5 C66 2019 Al252 Applying transfer learning for marine animal image classification using pre-trained convolutional neural network [thesis] / | LG 221 D35 C66 A5 I54 2015 J974 Wim [thesis] : a web-based interactive instructional material for Information Technology Education Courses / | LG 221 D35 C66 A5 I54 2024 Am72 Assets monitoring systems / | LG 221 D35 C66 A5 I54 2024 B4658 Fueventtracker [thesis] / |
Thesis Undergraduate (BS Computer Science) -- Foundation University, 2019.
Includes bibliographical references and appendices.
This study aims to classify each image into its class of marine animals and to determine the accuracy pf the image classifier. The image classifier applies Transfer Learning using a pre-trained Convolutional Neural Network. Transfer learning is using existing labeled data gained from solving one problem and then apply it to a different but related problem. In applying transfer learning, the researchers use a pre-trained Convolutional Neural Network. This machine learning algorithm is used because of its benefit in detecting patterns from images in order to recognize objects. In addition, they eliminate the need for manual feature extraction and they can be trained for new recognition tasks which let the researchers enable the use of pre-trained models.
There are no comments on this title.