Researching | Fine-Grained Fish Disease Image Recognition Algorithm Model

Laser & Optoelectronics Progress, Volume. 60, Issue 16, 1610005(2023)

Fine-Grained Fish Disease Image Recognition Algorithm Model

Liming Wei^1、*, Kui Zhao¹, Ning Wang¹, Zhongyan Zhang², and Haipeng Cui²

Author Affiliations

¹Department of Information Science and Engineering, Ocean University of China, Qingdao 266100, Shandong, China

²Qingdao JARI Industrial Control Technology Co., Ltd., Qingdao 266071, Shandong, China

show less

Abstract Get PDF(in Chinese)

Figures&Tables (14)

References (25)

Paper Information

Figures & Tables(14)

Fig. 1. Fine grained fish disease identification model CViT-FDRM

Download full size

Fig. 2. embedding layer of CViT FDRM model

Download full size

Fig. 3. Model classification visualization

Download full size

Fig. 4. Transformer encoder layer of CViT-FDRM model

Download full size

Fig. 5. Visualization of algorithms calculation process

Download full size

Fig. 6. Schematic diagrams of fish epidemic disease

Download full size

Fig. 7. Comparison before and after treatment. (a) Data before image processing; (b) data after image processing

Download full size

Fig. 8. Training results of CViT-FDRM fine granular classification model

Download full size

Fig. 9. Classification confusion matrix of CViT-FDRM model

Download full size

Fig. 10. Classification results of BN and GN methods under different batches. (a) Classification results of BN; (b) classification results of GN

Download full size

Fig. 11. P-R curves of different normalization methods

Download full size

Table 1. Test machine configuration
View table
Table 1. Test machine configuration
Machine name CPU RAM GPU Operating system
LAPTOP-USO0EFMM AMD Ryzen 7 5800H with Radeon Graphics 3.20 GHz 16 GB NVIDIA GeForce RTX 3060 Laptop GPU 6144 MB Windows 11

Table 2. Classification effect of CViT-FDRM in FishData01 dataset

Table 2. Classification effect of CViT-FDRM in FishData01 dataset

Data size	Training set	Test set	Data category	$R_{a c c u r a c y}$	$R_{p r e c i s i o n}$	$R_{r e c a l l}$	$s_{F 1}$
2020	399	100	Infectious fish disease	0.9600	0.9505	0.9600	0.9552
	408	102	Non-parasitic fish disease	0.9902	0.9902	0.9902	0.9902
	406	101	Invasive fish disease	0.9703	0.9515	0.9703	0.9608
	403	101	Healthy fish	0.9604	0.9604	0.9604	0.9604
Average				0.9702	0.9632	0.9702	0.9667

Table 3. Comparison of classification effects of classical models

Table 3. Comparison of classification effects of classical models

Model	Accuracy	Params /10⁶	Flops /10⁹	Time /ms
MobileNetV2	0.8694	6.9	0.46	122
MobileNetV3	0.9103	4.1	0.22	60
EfficientNet-b2	0.9225	7.8	0.87	145
ShuffleNetV2	0.8541	5.6	0.79	136
ResNet18	0.9371	11.6	1.71	215
Vit-small	0.9414	21	4.20	380
CViT-FDRM	0.9542	8.9	1.29	159

Tools

Get Citation

Copy Citation Text

Liming Wei, Kui Zhao, Ning Wang, Zhongyan Zhang, Haipeng Cui. Fine-Grained Fish Disease Image Recognition Algorithm Model[J]. Laser & Optoelectronics Progress, 2023, 60(16): 1610005

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites

Paper Information

Category: Image Processing

Received: Sep. 26, 2022

Accepted: Nov. 23, 2022

Published Online: Aug. 15, 2023

The Author Email: Liming Wei (15865569879@163.com)

DOI:10.3788/LOP222630

Topics

laser devices and laser physics

Lasers and Laser Optics

laser manufacturing

Instrumentation, Measurement and Metrology