A Vision-Based Method Utilizing Deep Convolutional Neural Networks for Fruit Variety Classification in Uncertainty Conditions of Retail Sales
This study proposes a double-track method for the classification of fruit varieties for application in retail sales. The method uses two nine-layer Convolutional Neural Networks (CNNs) with the same architecture, but different weight matrices. The first network classifies fruits according to images...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-09-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/9/19/3971 |
| _version_ | 1811320407189356544 |
|---|---|
| author | Rudnik Katarzyna Michalski Paweł |
| author_facet | Rudnik Katarzyna Michalski Paweł |
| author_sort | Rudnik Katarzyna |
| collection | DOAJ |
| description | This study proposes a double-track method for the classification of fruit varieties for application in retail sales. The method uses two nine-layer Convolutional Neural Networks (CNNs) with the same architecture, but different weight matrices. The first network classifies fruits according to images of fruits with a background, and the second network classifies based on images with the ROI (Region Of Interest, a single fruit). The results are aggregated with the proposed values of weights (importance). Consequently, the method returns the predicted class membership with the Certainty Factor (<i>CF</i>). The use of the certainty factor associated with prediction results from the original images and cropped ROIs is the main contribution of this paper. It has been shown that <i>CF</i>s indicate the correctness of the classification result and represent a more reliable measure compared to the probabilities on the CNN outputs. The method is tested with a dataset containing images of six apple varieties. The overall image classification accuracy for this testing dataset is excellent (99.78%). In conclusion, the proposed method is highly successful at recognizing unambiguous, ambiguous, and uncertain classifications, and it can be used in a vision-based sales systems in uncertain conditions and unplanned situations. |
| first_indexed | 2024-04-13T12:58:05Z |
| format | Article |
| id | doaj.art-eabce9fd14b141cb9cdc224970cb70eb |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-04-13T12:58:05Z |
| publishDate | 2019-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-eabce9fd14b141cb9cdc224970cb70eb2022-12-22T02:45:59ZengMDPI AGApplied Sciences2076-34172019-09-01919397110.3390/app9193971app9193971A Vision-Based Method Utilizing Deep Convolutional Neural Networks for Fruit Variety Classification in Uncertainty Conditions of Retail SalesRudnik Katarzyna0Michalski Paweł1Faculty of Production Engineering and Logistics, Opole University of Technology, 45-758 Opole, PolandFaculty of Electrical Engineering Automatic Control and Informatics, Opole University of Technology, 45-758 Opole, PolandThis study proposes a double-track method for the classification of fruit varieties for application in retail sales. The method uses two nine-layer Convolutional Neural Networks (CNNs) with the same architecture, but different weight matrices. The first network classifies fruits according to images of fruits with a background, and the second network classifies based on images with the ROI (Region Of Interest, a single fruit). The results are aggregated with the proposed values of weights (importance). Consequently, the method returns the predicted class membership with the Certainty Factor (<i>CF</i>). The use of the certainty factor associated with prediction results from the original images and cropped ROIs is the main contribution of this paper. It has been shown that <i>CF</i>s indicate the correctness of the classification result and represent a more reliable measure compared to the probabilities on the CNN outputs. The method is tested with a dataset containing images of six apple varieties. The overall image classification accuracy for this testing dataset is excellent (99.78%). In conclusion, the proposed method is highly successful at recognizing unambiguous, ambiguous, and uncertain classifications, and it can be used in a vision-based sales systems in uncertain conditions and unplanned situations.https://www.mdpi.com/2076-3417/9/19/3971convolutional neural networkdeep neural networkfruit classificationfruit recognitioncertainty factor |
| spellingShingle | Rudnik Katarzyna Michalski Paweł A Vision-Based Method Utilizing Deep Convolutional Neural Networks for Fruit Variety Classification in Uncertainty Conditions of Retail Sales Applied Sciences convolutional neural network deep neural network fruit classification fruit recognition certainty factor |
| title | A Vision-Based Method Utilizing Deep Convolutional Neural Networks for Fruit Variety Classification in Uncertainty Conditions of Retail Sales |
| title_full | A Vision-Based Method Utilizing Deep Convolutional Neural Networks for Fruit Variety Classification in Uncertainty Conditions of Retail Sales |
| title_fullStr | A Vision-Based Method Utilizing Deep Convolutional Neural Networks for Fruit Variety Classification in Uncertainty Conditions of Retail Sales |
| title_full_unstemmed | A Vision-Based Method Utilizing Deep Convolutional Neural Networks for Fruit Variety Classification in Uncertainty Conditions of Retail Sales |
| title_short | A Vision-Based Method Utilizing Deep Convolutional Neural Networks for Fruit Variety Classification in Uncertainty Conditions of Retail Sales |
| title_sort | vision based method utilizing deep convolutional neural networks for fruit variety classification in uncertainty conditions of retail sales |
| topic | convolutional neural network deep neural network fruit classification fruit recognition certainty factor |
| url | https://www.mdpi.com/2076-3417/9/19/3971 |
| work_keys_str_mv | AT rudnikkatarzyna avisionbasedmethodutilizingdeepconvolutionalneuralnetworksforfruitvarietyclassificationinuncertaintyconditionsofretailsales AT michalskipaweł avisionbasedmethodutilizingdeepconvolutionalneuralnetworksforfruitvarietyclassificationinuncertaintyconditionsofretailsales AT rudnikkatarzyna visionbasedmethodutilizingdeepconvolutionalneuralnetworksforfruitvarietyclassificationinuncertaintyconditionsofretailsales AT michalskipaweł visionbasedmethodutilizingdeepconvolutionalneuralnetworksforfruitvarietyclassificationinuncertaintyconditionsofretailsales |