Phenotyping Key Fruit Quality Traits in Olive Using RGB Images and Back Propagation Neural Networks
To predict oil and phenol concentrations in olive fruit, the combination of back propagation neural networks (BPNNs) and contact-less plant phenotyping techniques was employed to retrieve RGB image-based digital proxies of oil and phenol concentrations. Fruits of cultivars (×3) differing in ripening...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
American Association for the Advancement of Science (AAAS)
2023-01-01
|
| Series: | Plant Phenomics |
| Online Access: | https://spj.science.org/doi/10.34133/plantphenomics.0061 |
| _version_ | 1827917905529929728 |
|---|---|
| author | Giuseppe Montanaro Angelo Petrozza Laura Rustioni Francesco Cellini Vitale Nuzzo |
| author_facet | Giuseppe Montanaro Angelo Petrozza Laura Rustioni Francesco Cellini Vitale Nuzzo |
| author_sort | Giuseppe Montanaro |
| collection | DOAJ |
| description | To predict oil and phenol concentrations in olive fruit, the combination of back propagation neural networks (BPNNs) and contact-less plant phenotyping techniques was employed to retrieve RGB image-based digital proxies of oil and phenol concentrations. Fruits of cultivars (×3) differing in ripening time were sampled (~10-day interval, ×2 years), pictured and analyzed for phenol and oil concentrations. Prior to this, fruit samples were pictured and images were segmented to extract the red (R), green (G), and blue (B) mean pixel values that were rearranged in 35 RGB-based colorimetric indexes. Three BPNNs were designed using as input variables (a) the original 35 RGB indexes, (b) the scores of principal components after a principal component analysis (PCA) pre-processing of those indexes, and (c) a reduced number (28) of the RGB indexes achieved after a sparse PCA. The results show that the predictions reached the highest mean R2 values ranging from 0.87 to 0.95 (oil) and from 0.81 to 0.90 (phenols) across the BPNNs. In addition to the R2, other performance metrics were calculated (root mean squared error and mean absolute error) and combined into a general performance indicator (GPI). The resulting rank of the GPI suggests that a BPNN with a specific topology might be designed for cultivars grouped according to their ripening period. The present study documented that an RGB-based image phenotyping can effectively predict key quality traits in olive fruit supporting the developing olive sector within a digital agriculture domain. |
| first_indexed | 2024-03-13T03:35:07Z |
| format | Article |
| id | doaj.art-2211c6b779cc43f7a72d90a85ece482f |
| institution | Directory Open Access Journal |
| issn | 2643-6515 |
| language | English |
| last_indexed | 2024-03-13T03:35:07Z |
| publishDate | 2023-01-01 |
| publisher | American Association for the Advancement of Science (AAAS) |
| record_format | Article |
| series | Plant Phenomics |
| spelling | doaj.art-2211c6b779cc43f7a72d90a85ece482f2023-06-23T19:56:53ZengAmerican Association for the Advancement of Science (AAAS)Plant Phenomics2643-65152023-01-01510.34133/plantphenomics.0061Phenotyping Key Fruit Quality Traits in Olive Using RGB Images and Back Propagation Neural NetworksGiuseppe Montanaro0Angelo Petrozza1Laura Rustioni2Francesco Cellini3Vitale Nuzzo4Università degli Studi della Basilicata, 85100 Potenza, Italy.ALSIA, Agenzia Lucana Sviluppo Innovazione in Agricoltura, Metapontum Agrobios Research Center, 75010 Metaponto, Italy.Department of Biological and Environmental Sciences and Technologies, University of Salento, Lecce, Italy.ALSIA, Agenzia Lucana Sviluppo Innovazione in Agricoltura, Metapontum Agrobios Research Center, 75010 Metaponto, Italy.Università degli Studi della Basilicata, 85100 Potenza, Italy.To predict oil and phenol concentrations in olive fruit, the combination of back propagation neural networks (BPNNs) and contact-less plant phenotyping techniques was employed to retrieve RGB image-based digital proxies of oil and phenol concentrations. Fruits of cultivars (×3) differing in ripening time were sampled (~10-day interval, ×2 years), pictured and analyzed for phenol and oil concentrations. Prior to this, fruit samples were pictured and images were segmented to extract the red (R), green (G), and blue (B) mean pixel values that were rearranged in 35 RGB-based colorimetric indexes. Three BPNNs were designed using as input variables (a) the original 35 RGB indexes, (b) the scores of principal components after a principal component analysis (PCA) pre-processing of those indexes, and (c) a reduced number (28) of the RGB indexes achieved after a sparse PCA. The results show that the predictions reached the highest mean R2 values ranging from 0.87 to 0.95 (oil) and from 0.81 to 0.90 (phenols) across the BPNNs. In addition to the R2, other performance metrics were calculated (root mean squared error and mean absolute error) and combined into a general performance indicator (GPI). The resulting rank of the GPI suggests that a BPNN with a specific topology might be designed for cultivars grouped according to their ripening period. The present study documented that an RGB-based image phenotyping can effectively predict key quality traits in olive fruit supporting the developing olive sector within a digital agriculture domain.https://spj.science.org/doi/10.34133/plantphenomics.0061 |
| spellingShingle | Giuseppe Montanaro Angelo Petrozza Laura Rustioni Francesco Cellini Vitale Nuzzo Phenotyping Key Fruit Quality Traits in Olive Using RGB Images and Back Propagation Neural Networks Plant Phenomics |
| title | Phenotyping Key Fruit Quality Traits in Olive Using RGB Images and Back Propagation Neural Networks |
| title_full | Phenotyping Key Fruit Quality Traits in Olive Using RGB Images and Back Propagation Neural Networks |
| title_fullStr | Phenotyping Key Fruit Quality Traits in Olive Using RGB Images and Back Propagation Neural Networks |
| title_full_unstemmed | Phenotyping Key Fruit Quality Traits in Olive Using RGB Images and Back Propagation Neural Networks |
| title_short | Phenotyping Key Fruit Quality Traits in Olive Using RGB Images and Back Propagation Neural Networks |
| title_sort | phenotyping key fruit quality traits in olive using rgb images and back propagation neural networks |
| url | https://spj.science.org/doi/10.34133/plantphenomics.0061 |
| work_keys_str_mv | AT giuseppemontanaro phenotypingkeyfruitqualitytraitsinoliveusingrgbimagesandbackpropagationneuralnetworks AT angelopetrozza phenotypingkeyfruitqualitytraitsinoliveusingrgbimagesandbackpropagationneuralnetworks AT laurarustioni phenotypingkeyfruitqualitytraitsinoliveusingrgbimagesandbackpropagationneuralnetworks AT francescocellini phenotypingkeyfruitqualitytraitsinoliveusingrgbimagesandbackpropagationneuralnetworks AT vitalenuzzo phenotypingkeyfruitqualitytraitsinoliveusingrgbimagesandbackpropagationneuralnetworks |