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

作     者：Yang Zhang Jun Yue Aihuan Song Shixiang Jia Zhenbo Li 

作者机构：School of Information and Electrical EngineeringLudong UniversityYantai 264025PR China Marine Biology Institute of Shandong ProvinceQingdao 266104PR China School of Information and Electrical EngineeringChina Agricultural UniversityBeijing 100193PR China 

出 版 物：《农业信息处理(英文)》 (Information Processing in Agriculture)

年 卷 期：2023年第10卷第2期

页      面：149-163页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：the joint support of the National Key R&D Program Blue Granary Technology Innovation Key Special Project(2020YFD0900204) the Yantai Key R&D Project(2019XDHZ084) 

主　　题：Shellfish recognition High similarity Unbalanced samples Convolutional Neural Network Filter pruning and repairing Hybrid loss function 

摘      要：The high similarity of shellfish images and unbalanced samples are key factors affecting the accuracy of shellfish *** 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 species and 93574 images,and then propose a filter pruning and repairing model driven by an output entropy and orthogonality measurement for the recognition of shellfish with high similarity features to improve the feature expression ability of valid *** the shellfish recognition with unbalanced samples,a hybrid loss function,including regularization term and focus loss term,is employed to reduce the weight of easily classified samples by controlling the shared weight of each sample species to the total *** experimental results show that the accuracy of shell-fish recognition of the proposed method is 93.95%,13.68%higher than the benchmark network(VGG16),and the accuracy of shellfish recognition is improved by 0.46%,17.41%,17.36%,4.46%,1.67%,and 1.03%respectively compared with AlexNet,GoogLeNet,ResNet50,SN_Net,MutualNet,and ResNeSt,which are used to verify the efficiency of the proposed method.