Hyperspectral Imaging for Minced Meat Classification Using Nonlinear Deep Features
Minced meat substitution is one of the most common forms of food fraud in the meat industry. Recently, Hyperspectral Imaging (HSI) has been used for the classification and identification of minced meat types. However, conventional methods are based only on spectral information and ignore the spatial...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-11-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/10/21/7783 |
| _version_ | 1827702941392306176 |
|---|---|
| author | Hamail Ayaz Muhammad Ahmad Manuel Mazzara Ahmed Sohaib |
| author_facet | Hamail Ayaz Muhammad Ahmad Manuel Mazzara Ahmed Sohaib |
| author_sort | Hamail Ayaz |
| collection | DOAJ |
| description | Minced meat substitution is one of the most common forms of food fraud in the meat industry. Recently, Hyperspectral Imaging (HSI) has been used for the classification and identification of minced meat types. However, conventional methods are based only on spectral information and ignore the spatial variability of the data. Moreover, these methods first tend to reduce the size of the data, which to some extent ignores the abstract level information and does not preserve the spatial information. Therefore, this work proposes a novel <i>Isos-bestic</i> wavelength reduction method for the different minced meat types, by retaining only Myoglobin pigments (Mb) in the meat spectra. A total of 60 HSI cubes are acquired using Fx 10 Hyperspectral sensor. For each HSI cube, a set of preprocessing schemes is applied to extract the Region of Interest (ROI) and spectral preprocessing, i.e., Golay filtering. Later, these preprocessed HSI cubes are fed into a 3D-Convolutional Neural Network (3D-CNN) model for nonlinear feature extraction and classification. The proposed pipeline outperformed several state-of-the-art methods, with an overall accuracy of <inline-formula><math display="inline"><semantics><mrow><mn>94.0</mn><mo>%</mo></mrow></semantics></math></inline-formula>. |
| first_indexed | 2024-03-10T15:07:33Z |
| format | Article |
| id | doaj.art-ed574903a0f940efabb85fce076b2d8d |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T15:07:33Z |
| publishDate | 2020-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-ed574903a0f940efabb85fce076b2d8d2023-11-20T19:37:47ZengMDPI AGApplied Sciences2076-34172020-11-011021778310.3390/app10217783Hyperspectral Imaging for Minced Meat Classification Using Nonlinear Deep FeaturesHamail Ayaz0Muhammad Ahmad1Manuel Mazzara2Ahmed Sohaib3Department of Computer Engineering, Khwaja Freed University of Engineering and Technology (KFUEIT), Rahim Yar Khan 64200, PakistanDepartment of Computer Sciences, National University of Computer and Emerging Sciences, Islamabad, Chiniot-Faisalabad Campus, Chiniot 35400, PakistanInstitute of Software Development and Engineering, Innopolis University, 420500 Innopolis, RussiaDepartment of Computer Engineering, Khwaja Freed University of Engineering and Technology (KFUEIT), Rahim Yar Khan 64200, PakistanMinced meat substitution is one of the most common forms of food fraud in the meat industry. Recently, Hyperspectral Imaging (HSI) has been used for the classification and identification of minced meat types. However, conventional methods are based only on spectral information and ignore the spatial variability of the data. Moreover, these methods first tend to reduce the size of the data, which to some extent ignores the abstract level information and does not preserve the spatial information. Therefore, this work proposes a novel <i>Isos-bestic</i> wavelength reduction method for the different minced meat types, by retaining only Myoglobin pigments (Mb) in the meat spectra. A total of 60 HSI cubes are acquired using Fx 10 Hyperspectral sensor. For each HSI cube, a set of preprocessing schemes is applied to extract the Region of Interest (ROI) and spectral preprocessing, i.e., Golay filtering. Later, these preprocessed HSI cubes are fed into a 3D-Convolutional Neural Network (3D-CNN) model for nonlinear feature extraction and classification. The proposed pipeline outperformed several state-of-the-art methods, with an overall accuracy of <inline-formula><math display="inline"><semantics><mrow><mn>94.0</mn><mo>%</mo></mrow></semantics></math></inline-formula>.https://www.mdpi.com/2076-3417/10/21/7783minced meatclassificationdeep learningmyoglobin spectral features<i>isos-bestic</i> wavelength reduction |
| spellingShingle | Hamail Ayaz Muhammad Ahmad Manuel Mazzara Ahmed Sohaib Hyperspectral Imaging for Minced Meat Classification Using Nonlinear Deep Features Applied Sciences minced meat classification deep learning myoglobin spectral features <i>isos-bestic</i> wavelength reduction |
| title | Hyperspectral Imaging for Minced Meat Classification Using Nonlinear Deep Features |
| title_full | Hyperspectral Imaging for Minced Meat Classification Using Nonlinear Deep Features |
| title_fullStr | Hyperspectral Imaging for Minced Meat Classification Using Nonlinear Deep Features |
| title_full_unstemmed | Hyperspectral Imaging for Minced Meat Classification Using Nonlinear Deep Features |
| title_short | Hyperspectral Imaging for Minced Meat Classification Using Nonlinear Deep Features |
| title_sort | hyperspectral imaging for minced meat classification using nonlinear deep features |
| topic | minced meat classification deep learning myoglobin spectral features <i>isos-bestic</i> wavelength reduction |
| url | https://www.mdpi.com/2076-3417/10/21/7783 |
| work_keys_str_mv | AT hamailayaz hyperspectralimagingformincedmeatclassificationusingnonlineardeepfeatures AT muhammadahmad hyperspectralimagingformincedmeatclassificationusingnonlineardeepfeatures AT manuelmazzara hyperspectralimagingformincedmeatclassificationusingnonlineardeepfeatures AT ahmedsohaib hyperspectralimagingformincedmeatclassificationusingnonlineardeepfeatures |