A High-similarity shellfish recognition method based on convolutional neural network

The high similarity of shellfish images and unbalanced samples are key factors affecting the accuracy of shellfish recognition. This study proposes a new shellfish recognition method FL_Net based on a Convolutional Neural Network (CNN). We first establish the shellfish image (SI) dataset with 68 spe...

Full description

Bibliographic Details

Published in:	Information Processing in Agriculture
Main Authors:	Yang Zhang, Jun Yue, Aihuan Song, Shixiang Jia, Zhenbo Li
Format:	Article
Language:	English
Published:	Elsevier 2023-06-01
Subjects:	Shellfish recognition High similarity Unbalanced samples Convolutional Neural Network Filter pruning and repairing Hybrid loss function
Online Access:	http://www.sciencedirect.com/science/article/pii/S2214317322000555