| 基于鱼体特征点检测的淡水鱼种类识别 |
| |
| 引用本文： | 朱明,李梦珂,万鹏,肖畅宇,赵竣威.基于鱼体特征点检测的淡水鱼种类识别[J].农业工程学报,2023,39(11):155-164. |
| |
| 作者姓名： | 朱明 李梦珂 万鹏 肖畅宇 赵竣威 |
| |
| 作者单位： | 华中农业大学工学院, 武汉 430070;农业农村部水产养殖设施工程重点实验室, 武汉 430070;农业农村部长江中下游农业装备重点实验室, 武汉 430070;华中农业大学工学院, 武汉 430070;农业农村部水产养殖设施工程重点实验室, 武汉 430070;农业农村部长江中下游农业装备重点实验室, 武汉 430070;农业农村部华南现代农业智能装备重点实验室, 广州, 510630 |
| |
| 基金项目： | 国家重点研发计划项目（2022YFD2001705）；湖北省农机装备补短板核心技术应用攻关项目（HBSNYT202221）；湖北省农业科技创新中心2020年重大科技研发专项（2020-620-000-002-03）；农业农村部华南现代农业智能装备重点实验室开放基金课题资助(HNZJ202208) |
| |
| 摘 要： | 针对传统机器视觉技术对淡水鱼种类进行检测时特征提取过程复杂的问题，该研究提出了基于特征点检测的淡水鱼种类识别方法。以鳊、鳙、草鱼、鲢、鲤5种大宗淡水鱼为对象，构建了淡水鱼特征点检测数据集；以AlexNet模型为基础，通过减小卷积核尺寸、去除局部响应归一化、引入批量归一化、更换损失函数，构建了改进AlexNet模型用于特征点检测；并以特征点为依据提取特征值、构造特征向量，使用Fisher判别分析方法实现了淡水鱼的种类识别。试验结果表明：改进AlexNet模型在测试集上的归一化平均误差的均值为0.0099，阈值δ为0.02和0.03时的失败率F0.02、F0.03分别为2.50%和0.83%，具有较好的精准度和误差分布情况；基于该模型和Fisher判别分析的淡水鱼种类识别方法对5种淡水鱼的识别准确率为98.0%，单幅图像的平均识别时间为0.368 s，保证了时效性。由此可知，提出的改进AlexNet模型能实现淡水鱼的特征点检测并具有较高的精度，可为淡水鱼种类识别、尺寸检测、鱼体分割等提供条件，该方法可为淡水鱼自动化分类装置的研发奠定基础。
|
| 关 键 词： | 鱼 图像识别 深度学习 特征点检测 种类识别 Fisher判别分析 |
| 收稿时间： | 2023/1/18 0:00:00 |
| 修稿时间： | 2023/4/12 0:00:00 |
Identification of freshwater fish species based on fish feature point detection |
| |
| ZHU Ming,LI Mengke,WAN Peng,XIAO Changyu,ZHAO Junwei.Identification of freshwater fish species based on fish feature point detection[J].Transactions of the Chinese Society of Agricultural Engineering,2023,39(11):155-164. |
| |
| Authors: | ZHU Ming LI Mengke WAN Peng XIAO Changyu ZHAO Junwei |
| |
| Institution: | College of Engineering, Huazhong Agricultural University, Wuhan 430070, China;Key Laboratory of Aquaculture Facilities Engineering, Ministry of Agriculture and Rural Affairs, Wuhan 430070, China;Key Laboratory of Agricultural Equipment in Mid-lower Yangtze River, Ministry of Agriculture and Rural Affairs, Wuhan 430070, China;College of Engineering, Huazhong Agricultural University, Wuhan 430070, China;Key Laboratory of Aquaculture Facilities Engineering, Ministry of Agriculture and Rural Affairs, Wuhan 430070, China;Key Laboratory of Agricultural Equipment in Mid-lower Yangtze River, Ministry of Agriculture and Rural Affairs, Wuhan 430070, China;Key Laboratory of Modern Agricultural Intelligent Equipment in South China, Ministry of Agriculture and Rural Affairs, Guangzhou 510630, China |
| |
| Abstract: | An accurate and rapid identification of species is one of the most important parts of freshwater fish pre-treatment. However, deep learning-based freshwater fish classification cannot quantitatively describe the feature parameters of fish, due to the complicated feature extraction. This study aims to propose a deep learning-based fish feature point detection and freshwater fish classification. Firstly, an image acquisition device was built to acquire the images of five freshwater fish species: bream, bighead carp, grass carp, silver carp, and common carp. Secondly, the data enhancement was performed on the original images. LabelMe software was also used to label 20 feature points of the fish body, in order to construct a freshwater fish feature point detection dataset. The feature point of freshwater fish was detected using an improved AlexNet feature point detection model with the convolutional neural networks (CNN). The improved AlexNet model also adjusted the network structure of the traditional model, in order to accommodate the feature point detection task by the modified convolutional kernel size, the removal of the local response normalization layer, the addition of batch normalization layer, and the replacement of the loss function. The Euclidean distance between feature points was extracted as the feature value using the coordinates of the feature points. Feature vectors were constructed. Fisher discriminant analysis was used to identify the species of freshwater fish. A series of ablation experiments were conducted on the improved AlexNet model to clarify the impact of different improvement schemes on model performance. The results showed that the improved schemes were beneficial to improve the training efficiency and performance of the model. The average value of normalized mean error (NME) of the improved AlexNet model on the test set was 0.0099, the failure rate (FR) at thresholds of 0.02 and 0.03 were 2.50% and 0.83%, and the average detection time was 0.037 s, indicating the better accuracy and error distribution. The number of parameters and floating-point operations per second (FLOPs) of the improved AlexNet model were smaller than those of the VGG16 model. The test set detection was also better than that of the VGG16 model, compared with different feature extraction models. Although the number of parameters and FLOPs of the improved AlexNet model was larger, the average NME and the FR were lower than that of the MobileNetV2 model. The recognition accuracy of 98.0% was achieved in the freshwater fish species recognition using the model and Fisher discriminant analysis for five freshwater fish species. The average recognition time of a single image was 0.368s. The feature point detection model can be expected to detect the feature points of five species of freshwater fish with high accuracy. The finding can also facilitate freshwater fish species identification, size detection, and fish segmentation. The freshwater fish species identification using feature point detection and Fisher''s discriminant analysis can lay the foundation for the development of an automated freshwater fish classification device. |
| |
| Keywords: | fish image recognition deep learning feature point detection species recognition Fisher discriminant analysis |
|
| 点击此处可从《农业工程学报》浏览原始摘要信息 |
| 点击此处可从《农业工程学报》下载免费的PDF全文 |
|
