In the pork fat content detection task, traditional physical or chemical methods are strongly destructive, have substantial technical requirements and cannot achieve nondestructive detection without slaughtering. To solve these problems, we propose a novel, convenient and economical method for detecting the fat content of pig B-ultrasound images based on hybrid attention and multiscale fusion learning, which extracts and fuses shallow detail information and deep semantic information at multiple scales. First, a deep learning network is constructed to learn the salient features of fat images through a hybrid attention mechanism. Then, the information describing pork fat is extracted at multiple scales, and the detailed information expressed in the shallow layer and the semantic information expressed in the deep layer are fused later. Finally, a deep convolution network is used to predict the fat content compared with the real label. The experimental results show that the determination coefficient is greater than 0.95 on the 130 groups of pork B-ultrasound image data sets, which is 2.90, 6.10 and 5.13 percentage points higher than that of VGGNet, ResNet and DenseNet, respectively. It indicats that the model could effectively identify the B-ultrasound image of pigs and predict the fat content with high accuracy.
Wenxin DONG
Chongqing University of Technology
Jianxun ZHANG
Chongqing University of Technology
Shuqiu TAN
Chongqing University of Technology
Xinyue ZHANG
Northeastern University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Wenxin DONG, Jianxun ZHANG, Shuqiu TAN, Xinyue ZHANG, "Detection Method of Fat Content in Pig B-Ultrasound Based on Deep Learning" in IEICE TRANSACTIONS on Information,
vol. E106-D, no. 5, pp. 726-734, May 2023, doi: 10.1587/transinf.2022DLP0022.
Abstract: In the pork fat content detection task, traditional physical or chemical methods are strongly destructive, have substantial technical requirements and cannot achieve nondestructive detection without slaughtering. To solve these problems, we propose a novel, convenient and economical method for detecting the fat content of pig B-ultrasound images based on hybrid attention and multiscale fusion learning, which extracts and fuses shallow detail information and deep semantic information at multiple scales. First, a deep learning network is constructed to learn the salient features of fat images through a hybrid attention mechanism. Then, the information describing pork fat is extracted at multiple scales, and the detailed information expressed in the shallow layer and the semantic information expressed in the deep layer are fused later. Finally, a deep convolution network is used to predict the fat content compared with the real label. The experimental results show that the determination coefficient is greater than 0.95 on the 130 groups of pork B-ultrasound image data sets, which is 2.90, 6.10 and 5.13 percentage points higher than that of VGGNet, ResNet and DenseNet, respectively. It indicats that the model could effectively identify the B-ultrasound image of pigs and predict the fat content with high accuracy.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2022DLP0022/_p
Copy
@ARTICLE{e106-d_5_726,
author={Wenxin DONG, Jianxun ZHANG, Shuqiu TAN, Xinyue ZHANG, },
journal={IEICE TRANSACTIONS on Information},
title={Detection Method of Fat Content in Pig B-Ultrasound Based on Deep Learning},
year={2023},
volume={E106-D},
number={5},
pages={726-734},
abstract={In the pork fat content detection task, traditional physical or chemical methods are strongly destructive, have substantial technical requirements and cannot achieve nondestructive detection without slaughtering. To solve these problems, we propose a novel, convenient and economical method for detecting the fat content of pig B-ultrasound images based on hybrid attention and multiscale fusion learning, which extracts and fuses shallow detail information and deep semantic information at multiple scales. First, a deep learning network is constructed to learn the salient features of fat images through a hybrid attention mechanism. Then, the information describing pork fat is extracted at multiple scales, and the detailed information expressed in the shallow layer and the semantic information expressed in the deep layer are fused later. Finally, a deep convolution network is used to predict the fat content compared with the real label. The experimental results show that the determination coefficient is greater than 0.95 on the 130 groups of pork B-ultrasound image data sets, which is 2.90, 6.10 and 5.13 percentage points higher than that of VGGNet, ResNet and DenseNet, respectively. It indicats that the model could effectively identify the B-ultrasound image of pigs and predict the fat content with high accuracy.},
keywords={},
doi={10.1587/transinf.2022DLP0022},
ISSN={1745-1361},
month={May},}
Copy
TY - JOUR
TI - Detection Method of Fat Content in Pig B-Ultrasound Based on Deep Learning
T2 - IEICE TRANSACTIONS on Information
SP - 726
EP - 734
AU - Wenxin DONG
AU - Jianxun ZHANG
AU - Shuqiu TAN
AU - Xinyue ZHANG
PY - 2023
DO - 10.1587/transinf.2022DLP0022
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E106-D
IS - 5
JA - IEICE TRANSACTIONS on Information
Y1 - May 2023
AB - In the pork fat content detection task, traditional physical or chemical methods are strongly destructive, have substantial technical requirements and cannot achieve nondestructive detection without slaughtering. To solve these problems, we propose a novel, convenient and economical method for detecting the fat content of pig B-ultrasound images based on hybrid attention and multiscale fusion learning, which extracts and fuses shallow detail information and deep semantic information at multiple scales. First, a deep learning network is constructed to learn the salient features of fat images through a hybrid attention mechanism. Then, the information describing pork fat is extracted at multiple scales, and the detailed information expressed in the shallow layer and the semantic information expressed in the deep layer are fused later. Finally, a deep convolution network is used to predict the fat content compared with the real label. The experimental results show that the determination coefficient is greater than 0.95 on the 130 groups of pork B-ultrasound image data sets, which is 2.90, 6.10 and 5.13 percentage points higher than that of VGGNet, ResNet and DenseNet, respectively. It indicats that the model could effectively identify the B-ultrasound image of pigs and predict the fat content with high accuracy.
ER -