Research on the Classification Method of Tea Tree Seeds Quality Based on Mid-Infrared Spectroscopy and Improved DenseNet
Precise quality screening of tea tree seeds is crucial for the development of the tea industry. This study proposes a high-precision quality classification method for tea tree seeds by integrating mid-infrared (MIR) spectroscopy with an improved deep learning model. Four types of tea tree seeds in d...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-06-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/13/7336 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849704110337556480 |
|---|---|
| author | Di Deng Hao Li Jiawei Luo Jiachen Jiang Hongbo Mu |
| author_facet | Di Deng Hao Li Jiawei Luo Jiachen Jiang Hongbo Mu |
| author_sort | Di Deng |
| collection | DOAJ |
| description | Precise quality screening of tea tree seeds is crucial for the development of the tea industry. This study proposes a high-precision quality classification method for tea tree seeds by integrating mid-infrared (MIR) spectroscopy with an improved deep learning model. Four types of tea tree seeds in different states were prepared, and their spectral data were collected and preprocessed using Savitzky–Golay (SG) filtering and wavelet transform. Aiming at the deficiencies of DenseNet121 in one-dimensional spectral processing, such as insufficient generalization ability and weak feature extraction, the ECA-DenseNet model was proposed. Based on DenseNet121, the Batch Channel Normalization (BCN) module was introduced to reduce the dimensionality via 1 × 1 convolution while preserving the feature extraction capabilities, the Attention–Convolution Mix (ACMix) module was integrated to combine convolution and self-attention, and the Efficient Channel Attention (ECA) mechanism was utilized to enhance the feature discriminability. Experiments show that ECA-DenseNet achieves 99% accuracy, recall, and F1-score for classifying the four seed quality types, outperforming the original DenseNet121, machine learning models, and deep learning models. This study provides an efficient solution for tea tree seeds detection and screening, and its modular design can serve as a reference for the spectral classification of other crops. |
| format | Article |
| id | doaj-art-48b7c293a3a5475eb52422aed2c3abb9 |
| institution | DOAJ |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-48b7c293a3a5475eb52422aed2c3abb92025-08-20T03:16:52ZengMDPI AGApplied Sciences2076-34172025-06-011513733610.3390/app15137336Research on the Classification Method of Tea Tree Seeds Quality Based on Mid-Infrared Spectroscopy and Improved DenseNetDi Deng0Hao Li1Jiawei Luo2Jiachen Jiang3Hongbo Mu4College of Science, Northeast Forestry University, Harbin 150040, ChinaCollege of Science, Northeast Forestry University, Harbin 150040, ChinaCollege of Science, Northeast Forestry University, Harbin 150040, ChinaCollege of Science, Northeast Forestry University, Harbin 150040, ChinaCollege of Science, Northeast Forestry University, Harbin 150040, ChinaPrecise quality screening of tea tree seeds is crucial for the development of the tea industry. This study proposes a high-precision quality classification method for tea tree seeds by integrating mid-infrared (MIR) spectroscopy with an improved deep learning model. Four types of tea tree seeds in different states were prepared, and their spectral data were collected and preprocessed using Savitzky–Golay (SG) filtering and wavelet transform. Aiming at the deficiencies of DenseNet121 in one-dimensional spectral processing, such as insufficient generalization ability and weak feature extraction, the ECA-DenseNet model was proposed. Based on DenseNet121, the Batch Channel Normalization (BCN) module was introduced to reduce the dimensionality via 1 × 1 convolution while preserving the feature extraction capabilities, the Attention–Convolution Mix (ACMix) module was integrated to combine convolution and self-attention, and the Efficient Channel Attention (ECA) mechanism was utilized to enhance the feature discriminability. Experiments show that ECA-DenseNet achieves 99% accuracy, recall, and F1-score for classifying the four seed quality types, outperforming the original DenseNet121, machine learning models, and deep learning models. This study provides an efficient solution for tea tree seeds detection and screening, and its modular design can serve as a reference for the spectral classification of other crops.https://www.mdpi.com/2076-3417/15/13/7336tea tree seeds quality screeningmid-infrared spectroscopyimproved DenseNet model |
| spellingShingle | Di Deng Hao Li Jiawei Luo Jiachen Jiang Hongbo Mu Research on the Classification Method of Tea Tree Seeds Quality Based on Mid-Infrared Spectroscopy and Improved DenseNet Applied Sciences tea tree seeds quality screening mid-infrared spectroscopy improved DenseNet model |
| title | Research on the Classification Method of Tea Tree Seeds Quality Based on Mid-Infrared Spectroscopy and Improved DenseNet |
| title_full | Research on the Classification Method of Tea Tree Seeds Quality Based on Mid-Infrared Spectroscopy and Improved DenseNet |
| title_fullStr | Research on the Classification Method of Tea Tree Seeds Quality Based on Mid-Infrared Spectroscopy and Improved DenseNet |
| title_full_unstemmed | Research on the Classification Method of Tea Tree Seeds Quality Based on Mid-Infrared Spectroscopy and Improved DenseNet |
| title_short | Research on the Classification Method of Tea Tree Seeds Quality Based on Mid-Infrared Spectroscopy and Improved DenseNet |
| title_sort | research on the classification method of tea tree seeds quality based on mid infrared spectroscopy and improved densenet |
| topic | tea tree seeds quality screening mid-infrared spectroscopy improved DenseNet model |
| url | https://www.mdpi.com/2076-3417/15/13/7336 |
| work_keys_str_mv | AT dideng researchontheclassificationmethodofteatreeseedsqualitybasedonmidinfraredspectroscopyandimproveddensenet AT haoli researchontheclassificationmethodofteatreeseedsqualitybasedonmidinfraredspectroscopyandimproveddensenet AT jiaweiluo researchontheclassificationmethodofteatreeseedsqualitybasedonmidinfraredspectroscopyandimproveddensenet AT jiachenjiang researchontheclassificationmethodofteatreeseedsqualitybasedonmidinfraredspectroscopyandimproveddensenet AT hongbomu researchontheclassificationmethodofteatreeseedsqualitybasedonmidinfraredspectroscopyandimproveddensenet |