Automatic Differentiating of Postharvest Banana Fruits with High Traits Using Imagery Data
Visually differentiating banana cultivar with high similarity in shape, color and peel texture requires skill and experience during harvesting to reduce mistake on identifying cultivar. This study aims to identify automatically some similar banana cultivars using banana finger imagery and computer v...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Universitas Brawijaya
2022-05-01
|
| Series: | AGRIVITA Journal of Agricultural Science |
| Subjects: | |
| Online Access: | https://agrivita.ub.ac.id/index.php/agrivita/article/view/3648 |
| _version_ | 1811313550903214080 |
|---|---|
| author | Candra Dewi Wayan Firdaus Mahmudy Solimun Solimun Endang Arisoesilaningsih |
| author_facet | Candra Dewi Wayan Firdaus Mahmudy Solimun Solimun Endang Arisoesilaningsih |
| author_sort | Candra Dewi |
| collection | DOAJ |
| description | Visually differentiating banana cultivar with high similarity in shape, color and peel texture requires skill and experience during harvesting to reduce mistake on identifying cultivar. This study aims to identify automatically some similar banana cultivars using banana finger imagery and computer vision. The identification process was carried out to distinguish two groups of bananas with high similarities, namely group 1 (Ambon, Hijau, Goroho) and group 2 (Barlin, Mas). The test was conducted on the pair of datasets of unripe Ambon-Hijau-Goroho, ripe Hijau-Goroho, ripe and unripe Barlin-Mas. Testing was done to determine the performance of identification and to find out the most effective characteristics that could be used as cultivar identification. Results of classification using extreme learning machine (ELM) showed that texture features extracted from local binary pattern (LBP) could accurately distinguish unripe Ambon-Goroho, unripe Goroho-Hijau, ripe Goroho-Hijau with 100% accuracy. While unripe Ambon-Hijau, unripe Barlin-Mas and ripe Barlin-Mas could be optimally distinguished using a combination of shape and peel texture features with accuracy of 93.39%, 89.68%, 99.31% respectively. This result indicated that the proposed method could be used as an alternative of automatic banana sortation during post-harvest. The use of shape and peel texture features had shown effectively differentiating these high similarity banana cultivars. |
| first_indexed | 2024-04-13T10:55:42Z |
| format | Article |
| id | doaj.art-8a687fff72e04468bc98acaedaab4b97 |
| institution | Directory Open Access Journal |
| issn | 0126-0537 2477-8516 |
| language | English |
| last_indexed | 2024-04-13T10:55:42Z |
| publishDate | 2022-05-01 |
| publisher | Universitas Brawijaya |
| record_format | Article |
| series | AGRIVITA Journal of Agricultural Science |
| spelling | doaj.art-8a687fff72e04468bc98acaedaab4b972022-12-22T02:49:32ZengUniversitas BrawijayaAGRIVITA Journal of Agricultural Science0126-05372477-85162022-05-0144227628910.17503/agrivita.v44i2.3648666Automatic Differentiating of Postharvest Banana Fruits with High Traits Using Imagery DataCandra Dewi0Wayan Firdaus Mahmudy1Solimun Solimun2Endang Arisoesilaningsih3Department of Biology, Faculty of Mathematics and Natural Sciences, Universitas Brawijaya, Malang, East Java, Indonesia Department of Informatics Engineering, Faculty of Computer Science, Universitas Brawijaya, Malang, East Java, IndonesiaDepartment of Informatics Engineering, Faculty of Computer Science, Universitas Brawijaya, Malang, East Java, IndonesiaDepartment of Statistics, Faculty of Mathematics and Science, Universitas Brawijaya, Malang, East Java, IndonesiaDepartment of Biology, Faculty of Mathematics and Natural Sciences, Universitas Brawijaya, Malang, East Java, IndonesiaVisually differentiating banana cultivar with high similarity in shape, color and peel texture requires skill and experience during harvesting to reduce mistake on identifying cultivar. This study aims to identify automatically some similar banana cultivars using banana finger imagery and computer vision. The identification process was carried out to distinguish two groups of bananas with high similarities, namely group 1 (Ambon, Hijau, Goroho) and group 2 (Barlin, Mas). The test was conducted on the pair of datasets of unripe Ambon-Hijau-Goroho, ripe Hijau-Goroho, ripe and unripe Barlin-Mas. Testing was done to determine the performance of identification and to find out the most effective characteristics that could be used as cultivar identification. Results of classification using extreme learning machine (ELM) showed that texture features extracted from local binary pattern (LBP) could accurately distinguish unripe Ambon-Goroho, unripe Goroho-Hijau, ripe Goroho-Hijau with 100% accuracy. While unripe Ambon-Hijau, unripe Barlin-Mas and ripe Barlin-Mas could be optimally distinguished using a combination of shape and peel texture features with accuracy of 93.39%, 89.68%, 99.31% respectively. This result indicated that the proposed method could be used as an alternative of automatic banana sortation during post-harvest. The use of shape and peel texture features had shown effectively differentiating these high similarity banana cultivars.https://agrivita.ub.ac.id/index.php/agrivita/article/view/3648banana fingerclassificationhigh similarityshape featuretexture feature |
| spellingShingle | Candra Dewi Wayan Firdaus Mahmudy Solimun Solimun Endang Arisoesilaningsih Automatic Differentiating of Postharvest Banana Fruits with High Traits Using Imagery Data AGRIVITA Journal of Agricultural Science banana finger classification high similarity shape feature texture feature |
| title | Automatic Differentiating of Postharvest Banana Fruits with High Traits Using Imagery Data |
| title_full | Automatic Differentiating of Postharvest Banana Fruits with High Traits Using Imagery Data |
| title_fullStr | Automatic Differentiating of Postharvest Banana Fruits with High Traits Using Imagery Data |
| title_full_unstemmed | Automatic Differentiating of Postharvest Banana Fruits with High Traits Using Imagery Data |
| title_short | Automatic Differentiating of Postharvest Banana Fruits with High Traits Using Imagery Data |
| title_sort | automatic differentiating of postharvest banana fruits with high traits using imagery data |
| topic | banana finger classification high similarity shape feature texture feature |
| url | https://agrivita.ub.ac.id/index.php/agrivita/article/view/3648 |
| work_keys_str_mv | AT candradewi automaticdifferentiatingofpostharvestbananafruitswithhightraitsusingimagerydata AT wayanfirdausmahmudy automaticdifferentiatingofpostharvestbananafruitswithhightraitsusingimagerydata AT solimunsolimun automaticdifferentiatingofpostharvestbananafruitswithhightraitsusingimagerydata AT endangarisoesilaningsih automaticdifferentiatingofpostharvestbananafruitswithhightraitsusingimagerydata |