Image retrieve for dolphins and whales based on EfficientNet network

Tong Zhou; Shengyang Li; Tian Bo; Yeming Cai

doi:10.1117/12.3004330

11 October 2023 Image retrieve for dolphins and whales based on EfficientNet network

Tong Zhou, Shengyang Li, Tian Bo, Yeming Cai

Proceedings Volume 12800, Sixth International Conference on Computer Information Science and Application Technology (CISAT 2023); 128004Z (2023) https://doi.org/10.1117/12.3004330
Event: 6th International Conference on Computer Information Science and Application Technology (CISAT 2023), 2023, Hangzhou, China

Abstract

Image retrieve model for whales and dolphins, based on deep learning algorithms, analyzes features such as body shape, size, color, and tails to accurately classify images of different species. The technology has potential applications for scientific research, conservation, and marine wildlife management. It can help authorities identify species at risk of ship collision and reduce entanglement in fishing gear. Deep learning relies on large datasets to develop effective image retrieval models. We propose a network detects dorsal fins of whales and dolphins via feature extraction and image retrieval techniques. Architecture allows for efficient identification and outperforms comparison approaches like ResNet50 and EfficientNet B3, as evaluated on a dataset.

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Tong Zhou, Shengyang Li, Tian Bo, and Yeming Cai "Image retrieve for dolphins and whales based on EfficientNet network", Proc. SPIE 12800, Sixth International Conference on Computer Information Science and Application Technology (CISAT 2023), 128004Z (11 October 2023); https://doi.org/10.1117/12.3004330

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available