Semisupervised Deep Learning for the Detection of Foreign Materials on Poultry Meat with Near-Infrared Hyperspectral Imaging
A novel semisupervised hyperspectral imaging technique was developed to detect foreign materials (FMs) on raw poultry meat. Combining hyperspectral imaging and deep learning has shown promise in identifying food safety and quality attributes. However, the challenge lies in acquiring a large amount o...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-08-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/23/16/7014 |
_version_ | 1797583296361660416 |
---|---|
author | Rodrigo Louzada Campos Seung-Chul Yoon Soo Chung Suchendra M. Bhandarkar |
author_facet | Rodrigo Louzada Campos Seung-Chul Yoon Soo Chung Suchendra M. Bhandarkar |
author_sort | Rodrigo Louzada Campos |
collection | DOAJ |
description | A novel semisupervised hyperspectral imaging technique was developed to detect foreign materials (FMs) on raw poultry meat. Combining hyperspectral imaging and deep learning has shown promise in identifying food safety and quality attributes. However, the challenge lies in acquiring a large amount of accurately annotated/labeled data for model training. This paper proposes a novel semisupervised hyperspectral deep learning model based on a generative adversarial network, utilizing an improved 1D U-Net as its discriminator, to detect FMs on raw chicken breast fillets. The model was trained by using approximately 879,000 spectral responses from hyperspectral images of clean chicken breast fillets in the near-infrared wavelength range of 1000–1700 nm. Testing involved 30 different types of FMs commonly found in processing plants, prepared in two nominal sizes: 2 × 2 mm<sup>2</sup> and 5 × 5 mm<sup>2</sup>. The FM-detection technique achieved impressive results at both the spectral pixel level and the foreign material object level. At the spectral pixel level, the model achieved a precision of 100%, a recall of over 93%, an F1 score of 96.8%, and a balanced accuracy of 96.9%. When combining the rich 1D spectral data with 2D spatial information, the FM-detection accuracy at the object level reached 96.5%. In summary, the impressive results obtained through this study demonstrate its effectiveness at accurately identifying and localizing FMs. Furthermore, the technique’s potential for generalization and application to other agriculture and food-related domains highlights its broader significance. |
first_indexed | 2024-03-10T23:36:54Z |
format | Article |
id | doaj.art-b05ae6257b664dd08eaeda95b7427b0b |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-10T23:36:54Z |
publishDate | 2023-08-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-b05ae6257b664dd08eaeda95b7427b0b2023-11-19T02:55:32ZengMDPI AGSensors1424-82202023-08-012316701410.3390/s23167014Semisupervised Deep Learning for the Detection of Foreign Materials on Poultry Meat with Near-Infrared Hyperspectral ImagingRodrigo Louzada Campos0Seung-Chul Yoon1Soo Chung2Suchendra M. Bhandarkar3School of Computing, University of Georgia, Athens, GA 30602, USAU.S. National Poultry Research Center, Agricultural Research Service, U.S. Department of Agriculture, Athens, GA 30605, USADepartment of Biosystems Engineering, Integrated Major in Global Smart Farm, Research Institute of Agriculture and Life Sciences, Seoul National University, Seoul 08826, Republic of KoreaSchool of Computing, University of Georgia, Athens, GA 30602, USAA novel semisupervised hyperspectral imaging technique was developed to detect foreign materials (FMs) on raw poultry meat. Combining hyperspectral imaging and deep learning has shown promise in identifying food safety and quality attributes. However, the challenge lies in acquiring a large amount of accurately annotated/labeled data for model training. This paper proposes a novel semisupervised hyperspectral deep learning model based on a generative adversarial network, utilizing an improved 1D U-Net as its discriminator, to detect FMs on raw chicken breast fillets. The model was trained by using approximately 879,000 spectral responses from hyperspectral images of clean chicken breast fillets in the near-infrared wavelength range of 1000–1700 nm. Testing involved 30 different types of FMs commonly found in processing plants, prepared in two nominal sizes: 2 × 2 mm<sup>2</sup> and 5 × 5 mm<sup>2</sup>. The FM-detection technique achieved impressive results at both the spectral pixel level and the foreign material object level. At the spectral pixel level, the model achieved a precision of 100%, a recall of over 93%, an F1 score of 96.8%, and a balanced accuracy of 96.9%. When combining the rich 1D spectral data with 2D spatial information, the FM-detection accuracy at the object level reached 96.5%. In summary, the impressive results obtained through this study demonstrate its effectiveness at accurately identifying and localizing FMs. Furthermore, the technique’s potential for generalization and application to other agriculture and food-related domains highlights its broader significance.https://www.mdpi.com/1424-8220/23/16/7014chicken breast filletsdeep learningforeign material detectiongenerative adversarial networkhyperspectral imagingnear infrared |
spellingShingle | Rodrigo Louzada Campos Seung-Chul Yoon Soo Chung Suchendra M. Bhandarkar Semisupervised Deep Learning for the Detection of Foreign Materials on Poultry Meat with Near-Infrared Hyperspectral Imaging Sensors chicken breast fillets deep learning foreign material detection generative adversarial network hyperspectral imaging near infrared |
title | Semisupervised Deep Learning for the Detection of Foreign Materials on Poultry Meat with Near-Infrared Hyperspectral Imaging |
title_full | Semisupervised Deep Learning for the Detection of Foreign Materials on Poultry Meat with Near-Infrared Hyperspectral Imaging |
title_fullStr | Semisupervised Deep Learning for the Detection of Foreign Materials on Poultry Meat with Near-Infrared Hyperspectral Imaging |
title_full_unstemmed | Semisupervised Deep Learning for the Detection of Foreign Materials on Poultry Meat with Near-Infrared Hyperspectral Imaging |
title_short | Semisupervised Deep Learning for the Detection of Foreign Materials on Poultry Meat with Near-Infrared Hyperspectral Imaging |
title_sort | semisupervised deep learning for the detection of foreign materials on poultry meat with near infrared hyperspectral imaging |
topic | chicken breast fillets deep learning foreign material detection generative adversarial network hyperspectral imaging near infrared |
url | https://www.mdpi.com/1424-8220/23/16/7014 |
work_keys_str_mv | AT rodrigolouzadacampos semisuperviseddeeplearningforthedetectionofforeignmaterialsonpoultrymeatwithnearinfraredhyperspectralimaging AT seungchulyoon semisuperviseddeeplearningforthedetectionofforeignmaterialsonpoultrymeatwithnearinfraredhyperspectralimaging AT soochung semisuperviseddeeplearningforthedetectionofforeignmaterialsonpoultrymeatwithnearinfraredhyperspectralimaging AT suchendrambhandarkar semisuperviseddeeplearningforthedetectionofforeignmaterialsonpoultrymeatwithnearinfraredhyperspectralimaging |