skip to main content
10.1145/3467707.3467716acmotherconferencesArticle/Chapter ViewAbstractPublication PagesiccaiConference Proceedingsconference-collections
research-article

Research on Apple Variety Classification Based on the Combination of Hyperspectral and Deep Learning

Published: 24 September 2021 Publication History

Abstract

At present, the classification of apple varieties is mainly manual sorting. Due to the small differences between some apple types, manual discrimination has the problems of strong subjectivity, low efficiency and high cost. Therefore, in order to realize the real-time detection of apple varieties sold by merchants, the spectral data of different apple varieties were collected by the hyperspectral image acquisition system, and an automatic apple recognition model based on double-branch structure was proposed. One of the branches is the basic TCN network to extract the morphological information of the signal. The other branch is an enhancement module composed of two long and short-term memory networks (LSTM) to capture the timing characteristics of the signal. Then, the apple spectrum data under the feature band is input into the two branches at the same time, and the features from the two branches are merged using vector splicing, and finally the soft-max classifier is applied to output the network classification results. The experimental results show that the overall classification accuracy of seven kinds of apples reached 99.74%.

References

[1]
Shang, J., Zhang, Y., and Meng, Q. L. (2019). Nondestructive Identification of Apple Varieties by VIS/NIR Spectroscopy. Stor Proc, 19, 8-14. https://doi.org/BXJG201903002
[2]
Zou, X. B. and Zhao, J. W. (2007). Distinguishing cultivar apples by electronic nose based on multi-resolution decomposition and support vector machine. Chinese Journal of Scientific Instrument, 28, 534-538. https://doi.org/10.1007/s10483-007-0613-x
[3]
Ma, H. L., Wang, R. L., Cai, C., and Wang, D. (2017). Rapid Identification of Apple Varieties Based on Hyperspectral Imaging. T Chin Soc Agric Mach, 48, 305-312. https://doi.org/10.6041/j.issn.1000-1298.2017.04.040
[4]
Lei, H., Jiao, Z. Y., Ma, J. Q., Wu, L. S., and Zhong, Z. Y. (2020). Fast Recognition Algorithm of Apple Varieties Based on Multi Feature Fusion and SVM. Academic Research, 41, 13-17. https://doi.org/10.7666/d.y547998
[5]
Zhuang, J. J., Luo, S. M., Hou, C. J., Tang, Y., He, Y., and Xue, X. Y. (2018). Detection of orchard citrus fruits using a monocular machine vision-based method for utomatic fruit picking applications. COMPUT ELECTRON AGR, 152, 64-73. https://doi.org/10.1016/j.compag.2018.07.004
[6]
Geng, L., Ma, M. S., Xiao, Z. T., and Liu, Y. B. (2019). Jujube Classification Based on a Convolution Neural Network with Multichannel Weighting and Information Aggregation. Food Sci. Technol. Res., 25, 647-656. https://doi.org/10.3136/fstr.25.647
[7]
Yuan, M. X., Yu, H. T., Jiang, Y. F., Wang, Q., and Shen, Y. (2019). Apple maturity recognition combining transfer learning and adaptive learning rate. Journal of Chinese Agricultural Mechanization, 40, 131-135. https://doi.org/GLJH201911022
[8]
Wang, H. H., Li, C. Y., Mei, S. L., and Li, M. Z. (2012). Integrated calibration of line-scan high spectral imaging system for agricultural products. Transactions of the CSAE, 28, 244-249. https://doi.org/10.3969/j.issn.1002-6819.2012.14.037
[9]
Li, J. B., Rao, X. Q., Ying, Y. B., and Wang, D. T. (2010). Detection of navel oranges canker based on hyperspectral imaging technology. Transactions of the CSAE, 26, 222-228. https://doi.org/10.3969/j.issn.1002-6819.2010.08.038
[10]
Zhang, W., Pan, L. Q., and Tu, K. (2012). Detecting early embryo development of chicken hatching eggs by hyperspectral transmittance imaging. Transactions of the CSAE, 28, 149-155. https://doi.org/10.3969/j.issn.1002-6819.2012.21.021
[11]
Ioffe, S. and Szegedy, C. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. Computer Science. https://arxiv.org/abs/1502.03167
[12]
Lin, M., Chen, Q., and Yan, S. C. (2013). Network in network. Computer Science. https://arxiv.org/abs/1312.4400
[13]
Graves, A., Mohamed, A. R., and Hinton, G. (2013). Speech recognition with deep recurrent neural networks. In ICASSP, Vancouver, pp. 6645-6649. https://doi.org/10.1109/ICASSP.2013.6638947
[14]
Zhang, C., Pan, X., Li, H. P., Gardiner, A., Sargent, I., Hare, J., and Atkinson, P. M. (2018). A hybrid MLP-CNN classifier for very fine resolution remotely sensed image classification. ISPRS J. Photogramm. Remote Sens., 140, 133-144. https://doi.org/10.1016/j.isprsjprs.2017.07.014
[15]
Zhu, Z. H., Liu, T., Xie, D. J., Wang, Q. H., and Ma, M. H. (2015). Nondestructive detection of infertile hatching eggs based on spectral and imaging information. INT J AGR BIOL ENG, 8, 69-76. https://doi.org/10.3965/j.ijabe.20150804.1672

Cited By

View all
  • (2024)New Insights into Recent Trends and Emerging Technologies in Apple SortingACS Food Science & Technology10.1021/acsfoodscitech.3c005524:2(290-303)Online publication date: 24-Jan-2024
  • (2023)LSCA-net: A lightweight spectral convolution attention network for hyperspectral image processingComputers and Electronics in Agriculture10.1016/j.compag.2023.108382215(108382)Online publication date: Dec-2023

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences
ICCAI '21: Proceedings of the 2021 7th International Conference on Computing and Artificial Intelligence
April 2021
498 pages
ISBN:9781450389501
DOI:10.1145/3467707
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 24 September 2021

Permissions

Request permissions for this article.

Check for updates

Author Tags

  1. Apple variety classification
  2. Dual branch network
  3. Feature extraction
  4. Hyperspectral image
  5. TCN

Qualifiers

  • Research-article
  • Research
  • Refereed limited

Conference

ICCAI '21

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • Downloads (Last 12 months)8
  • Downloads (Last 6 weeks)1
Reflects downloads up to 17 Feb 2025

Other Metrics

Citations

Cited By

View all
  • (2024)New Insights into Recent Trends and Emerging Technologies in Apple SortingACS Food Science & Technology10.1021/acsfoodscitech.3c005524:2(290-303)Online publication date: 24-Jan-2024
  • (2023)LSCA-net: A lightweight spectral convolution attention network for hyperspectral image processingComputers and Electronics in Agriculture10.1016/j.compag.2023.108382215(108382)Online publication date: Dec-2023

View Options

Login options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

HTML Format

View this article in HTML Format.

HTML Format

Figures

Tables

Media

Share

Share

Share this Publication link

Share on social media