The fiber mouthfeel of fish muscle is a highly sought-after goal for surimi gel products.The primary aim of research and development has been to quickly and accurately evaluate fiber degree for fish muscle.Therefore,b...The fiber mouthfeel of fish muscle is a highly sought-after goal for surimi gel products.The primary aim of research and development has been to quickly and accurately evaluate fiber degree for fish muscle.Therefore,based on the ResNet model,edge feature attentional mechanism was introduced to obtain the edge feature attention net (EFANet) to evaluate fiber degree for fish muscle.The EFANet was trained and tested on a dataset,which was made by collecting microscopic pictures of fish samples with different degrees of breakage.Compared with the three classic convolutional neural network (CNN) models,the EFANet emphasizes the learning of fiber texture information for fish muscle,reduces the effect of image color change,and significantly improves the detection accuracy.The average accuracy and specificity of the EFANet-50 on the testing dataset were 96.22% and 97.92%,respectively,which proved that it can effectively predict the fiber degree of fish muscle.展开更多
基金financially supported by the National“Thirteenth Five-Year”Plan for Science&Technology(2019YFD0902000)the Major Science and Technology Planed Program Projects in Xiamen City(3502Z20201032)+3 种基金the Fund of Fujian Provincial Key Laboratory of Refrigeration and Conditioning Aquatic Products Processing(FPKLRCAPP2021-02)the Jiangsu Agricultural Science and Technology Innovation Fund(CX(21)2040)the National First-class Discipline Program of Food Science and Technology(JUFSTR20180102)the Collaborative Innovation Center of Food Safety and Quality Control in Jiangsu Province.
文摘The fiber mouthfeel of fish muscle is a highly sought-after goal for surimi gel products.The primary aim of research and development has been to quickly and accurately evaluate fiber degree for fish muscle.Therefore,based on the ResNet model,edge feature attentional mechanism was introduced to obtain the edge feature attention net (EFANet) to evaluate fiber degree for fish muscle.The EFANet was trained and tested on a dataset,which was made by collecting microscopic pictures of fish samples with different degrees of breakage.Compared with the three classic convolutional neural network (CNN) models,the EFANet emphasizes the learning of fiber texture information for fish muscle,reduces the effect of image color change,and significantly improves the detection accuracy.The average accuracy and specificity of the EFANet-50 on the testing dataset were 96.22% and 97.92%,respectively,which proved that it can effectively predict the fiber degree of fish muscle.
