• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

深度卷积神经网络在根据大部分脱水鱼图像预测长度、周长和重量方面的应用。

Applications of deep convolutional neural networks to predict length, circumference, and weight from mostly dewatered images of fish.

作者信息

Bravata Nicholas, Kelly Dylan, Eickholt Jesse, Bryan Janine, Miehls Scott, Zielinski Dan

机构信息

Department of Computer Science Central Michigan University Mount Pleasant MI USA.

Whooshh Innovations, Inc. Seattle WA USA.

出版信息

Ecol Evol. 2020 Aug 4;10(17):9313-9325. doi: 10.1002/ece3.6618. eCollection 2020 Sep.

DOI:10.1002/ece3.6618
PMID:32953063
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC7487224/
Abstract

Simple biometric data of fish aid fishery management tasks such as monitoring the structure of fish populations and regulating recreational harvest. While these data are foundational to fishery research and management, the collection of length and weight data through physical handling of the fish is challenging as it is time consuming for personnel and can be stressful for the fish. Recent advances in imaging technology and machine learning now offer alternatives for capturing biometric data. To investigate the potential of deep convolutional neural networks to predict biometric data, several regressors were trained and evaluated on data stemming from the FishL™ Recognition System and manual measurements of length, girth, and weight. The dataset consisted of 694 fish from 22 different species common to Laurentian Great Lakes. Even with such a diverse dataset and variety of presentations by the fish, the regressors proved to be robust and achieved competitive mean percent errors in the range of 5.5 to 7.6% for length and girth on an evaluation dataset. Potential applications of this work could increase the efficiency and accuracy of routine survey work by fishery professionals and provide a means for longer-term automated collection of fish biometric data.

摘要

鱼类的简单生物特征数据有助于渔业管理任务，如监测鱼群结构和规范休闲捕捞量。虽然这些数据是渔业研究和管理的基础，但通过对鱼进行物理处理来收集长度和重量数据具有挑战性，因为这对工作人员来说耗时较长，而且可能给鱼带来压力。成像技术和机器学习的最新进展现在为获取生物特征数据提供了替代方法。为了研究深度卷积神经网络预测生物特征数据的潜力，对几个回归器进行了训练，并根据来自FishL™识别系统的数据以及长度、周长和重量的手动测量数据进行了评估。该数据集由来自劳伦森五大湖常见的22个不同物种的694条鱼组成。即使有如此多样的数据集和鱼的各种呈现方式，回归器在评估数据集上的长度和周长平均百分比误差在5.5%至7.6%范围内，证明是稳健的，并取得了有竞争力的结果。这项工作的潜在应用可以提高渔业专业人员日常调查工作的效率和准确性，并提供一种长期自动收集鱼类生物特征数据的方法。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8ef3/7487224/5e7026a54304/ECE3-10-9313-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8ef3/7487224/963ff1a22546/ECE3-10-9313-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8ef3/7487224/e800038f5a2e/ECE3-10-9313-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8ef3/7487224/e1c1adbb2d9a/ECE3-10-9313-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8ef3/7487224/6b890b0d495a/ECE3-10-9313-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8ef3/7487224/062723a2cb94/ECE3-10-9313-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8ef3/7487224/e27576ee5530/ECE3-10-9313-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8ef3/7487224/945ae86b9f23/ECE3-10-9313-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8ef3/7487224/bdde25f17777/ECE3-10-9313-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8ef3/7487224/c4435f5a2647/ECE3-10-9313-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8ef3/7487224/45e3990aed8d/ECE3-10-9313-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8ef3/7487224/650ee23d0c9b/ECE3-10-9313-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8ef3/7487224/3068f821dc9c/ECE3-10-9313-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8ef3/7487224/5e7026a54304/ECE3-10-9313-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8ef3/7487224/963ff1a22546/ECE3-10-9313-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8ef3/7487224/e800038f5a2e/ECE3-10-9313-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8ef3/7487224/e1c1adbb2d9a/ECE3-10-9313-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8ef3/7487224/6b890b0d495a/ECE3-10-9313-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8ef3/7487224/062723a2cb94/ECE3-10-9313-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8ef3/7487224/e27576ee5530/ECE3-10-9313-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8ef3/7487224/945ae86b9f23/ECE3-10-9313-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8ef3/7487224/bdde25f17777/ECE3-10-9313-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8ef3/7487224/c4435f5a2647/ECE3-10-9313-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8ef3/7487224/45e3990aed8d/ECE3-10-9313-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8ef3/7487224/650ee23d0c9b/ECE3-10-9313-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8ef3/7487224/3068f821dc9c/ECE3-10-9313-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8ef3/7487224/5e7026a54304/ECE3-10-9313-g013.jpg

相似文献

1
Applications of deep convolutional neural networks to predict length, circumference, and weight from mostly dewatered images of fish.深度卷积神经网络在根据大部分脱水鱼图像预测长度、周长和重量方面的应用。
Ecol Evol. 2020 Aug 4;10(17):9313-9325. doi: 10.1002/ece3.6618. eCollection 2020 Sep.
2
MABAL: a Novel Deep-Learning Architecture for Machine-Assisted Bone Age Labeling.MABAL：一种用于机器辅助骨龄标注的新型深度学习架构。
J Digit Imaging. 2018 Aug;31(4):513-519. doi: 10.1007/s10278-018-0053-3.
3
Development and qualification of a machine learning algorithm for automated hair counting.开发和验证一种用于自动头发计数的机器学习算法。
Int J Cosmet Sci. 2021 Nov;43 Suppl 1:S34-S41. doi: 10.1111/ics.12735.
4
Animal Species Recognition with Deep Convolutional Neural Networks from Ecological Camera Trap Images.基于生态相机陷阱图像，利用深度卷积神经网络进行动物物种识别。
Animals (Basel). 2023 May 2;13(9):1526. doi: 10.3390/ani13091526.
5
Deep Learning Approach for Multimodal Biometric Recognition System Based on Fusion of Iris, Face, and Finger Vein Traits.基于虹膜、人脸和指静脉特征融合的深度学习多模态生物识别系统方法。
Sensors (Basel). 2020 Sep 27;20(19):5523. doi: 10.3390/s20195523.
6
Autokeras Approach: A Robust Automated Deep Learning Network for Diagnosis Disease Cases in Medical Images.自动Keras方法：一种用于医学图像中疾病病例诊断的强大自动深度学习网络。
J Imaging. 2023 Mar 8;9(3):64. doi: 10.3390/jimaging9030064.
7
Transfer of Learning from Vision to Touch: A Hybrid Deep Convolutional Neural Network for Visuo-Tactile 3D Object Recognition.从视觉到触觉的迁移学习：用于视触 3D 物体识别的混合深度卷积神经网络。
Sensors (Basel). 2020 Dec 27;21(1):113. doi: 10.3390/s21010113.
8
A novel end-to-end classifier using domain transferred deep convolutional neural networks for biomedical images.一种使用域转移深度卷积神经网络的新型端到端生物医学图像分类器。
Comput Methods Programs Biomed. 2017 Mar;140:283-293. doi: 10.1016/j.cmpb.2016.12.019. Epub 2017 Jan 6.
9
A Survey of Deep Convolutional Neural Networks Applied for Prediction of Plant Leaf Diseases.深度学习卷积神经网络在植物叶片病害预测中的应用综述。
Sensors (Basel). 2021 Jul 12;21(14):4749. doi: 10.3390/s21144749.
10
Learning physical properties of liquid crystals with deep convolutional neural networks.利用深度卷积神经网络学习液晶的物理性质。
Sci Rep. 2020 May 6;10(1):7664. doi: 10.1038/s41598-020-63662-9.

引用本文的文献

1
Exploring opportunities of Artificial Intelligence in aquaculture to meet increasing food demand.探索人工智能在水产养殖中的机遇以满足不断增长的食物需求。
Food Chem X. 2024 Mar 19;22:101309. doi: 10.1016/j.fochx.2024.101309. eCollection 2024 Jun 30.
2
3D Reconstruction of Fishes Using Coded Structured Light.基于编码结构光的鱼类三维重建
J Imaging. 2023 Sep 18;9(9):189. doi: 10.3390/jimaging9090189.
3
In-Water Fish Body-Length Measurement System Based on Stereo Vision.基于立体视觉的水中鱼体长度测量系统。

本文引用的文献

1
Deep learning.深度学习。
Nature. 2015 May 28;521(7553):436-44. doi: 10.1038/nature14539.
Sensors (Basel). 2023 Jul 12;23(14):6325. doi: 10.3390/s23146325.
4
An affordable and easy-to-use tool for automatic fish length and weight estimation in mariculture.一种经济实惠且易于使用的水产养殖中自动估计鱼类体长和体重的工具。
Sci Rep. 2022 Sep 19;12(1):15642. doi: 10.1038/s41598-022-19932-9.
5
Non-Intrusive Fish Weight Estimation in Turbid Water Using Deep Learning and Regression Models.基于深度学习和回归模型的浊水非侵入式鱼类体重估计
Sensors (Basel). 2022 Jul 10;22(14):5161. doi: 10.3390/s22145161.