Deep CNNBased Detection for Tea Clone Identification
One factor affecting the quality of tea is the selection of plant material that would be planted on the field. Clonal selection is a common way to produce tea with better quality. However, as a natural cross pollination species, tea often consists of various clones or progenies of cross-pollinated p...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Indonesian Institute of Sciences
2019-12-01
|
| Series: | Jurnal Elektronika dan Telekomunikasi |
| Subjects: | |
| Online Access: | https://www.jurnalet.com/jet/article/view/296 |
| _version_ | 1818789934847229952 |
|---|---|
| author | Ade Ramdan Endang Suryawati R. Budiarianto Suryo Kusumo Hilman F. Pardede Oka Mahendra Rico Dahlan Fani Fauziah Heri Syahrian |
| author_facet | Ade Ramdan Endang Suryawati R. Budiarianto Suryo Kusumo Hilman F. Pardede Oka Mahendra Rico Dahlan Fani Fauziah Heri Syahrian |
| author_sort | Ade Ramdan |
| collection | DOAJ |
| description | One factor affecting the quality of tea is the selection of plant material that would be planted on the field. Clonal selection is a common way to produce tea with better quality. However, as a natural cross pollination species, tea often consists of various clones or progenies of cross-pollinated process. This commonly occurs on plantations owned by smallholder farmers. To produce a consistent quality tea, the clones or progenies need to be identified. Usually, human experts distinguish the plants from leaves by visual inspection on the physical attributes of the leaves, such as the textures, the bone structures, and the colors. It is very difficult for non-experts or common farmers to do such identifications. In this, we propose a deep learning-based identification of tea clones. We apply deep convolutional neural network (CNN) to identify 3 types of tea clones of Gambung series, a series of tea clones developed at Research Institute of Tea and Cinchona. Our study indicates that the performance of the CNN systems are affected by the depth of the convolutional layers. VGGNet, a popular CNN architectures with 16 layers, achieves better accuracy compared to AlexNet, a CNN with 6 layers. |
| first_indexed | 2024-12-18T14:47:27Z |
| format | Article |
| id | doaj.art-137c0f26858a499db6346c87b997865f |
| institution | Directory Open Access Journal |
| issn | 1411-8289 2527-9955 |
| language | English |
| last_indexed | 2024-12-18T14:47:27Z |
| publishDate | 2019-12-01 |
| publisher | Indonesian Institute of Sciences |
| record_format | Article |
| series | Jurnal Elektronika dan Telekomunikasi |
| spelling | doaj.art-137c0f26858a499db6346c87b997865f2022-12-21T21:04:15ZengIndonesian Institute of SciencesJurnal Elektronika dan Telekomunikasi1411-82892527-99552019-12-01192455010.14203/jet.v19.45-50164Deep CNNBased Detection for Tea Clone IdentificationAde Ramdan0Endang Suryawati1R. Budiarianto Suryo Kusumo2Hilman F. Pardede3Oka Mahendra4Rico Dahlan5Fani Fauziah6Heri Syahrian7Research Center for Informatics - LIPIResearch Center for Informatics - LIPIResearch Center for Informatics - LIPIResearch Center for Informatics - LIPITechnical Implementation Unit for Instrumentation Development - LIPIResearch Center for Electronics and Telecommunication - LIPIResearch Institute for Tea and CinchonaResearch Institute for Tea and CinchonaOne factor affecting the quality of tea is the selection of plant material that would be planted on the field. Clonal selection is a common way to produce tea with better quality. However, as a natural cross pollination species, tea often consists of various clones or progenies of cross-pollinated process. This commonly occurs on plantations owned by smallholder farmers. To produce a consistent quality tea, the clones or progenies need to be identified. Usually, human experts distinguish the plants from leaves by visual inspection on the physical attributes of the leaves, such as the textures, the bone structures, and the colors. It is very difficult for non-experts or common farmers to do such identifications. In this, we propose a deep learning-based identification of tea clones. We apply deep convolutional neural network (CNN) to identify 3 types of tea clones of Gambung series, a series of tea clones developed at Research Institute of Tea and Cinchona. Our study indicates that the performance of the CNN systems are affected by the depth of the convolutional layers. VGGNet, a popular CNN architectures with 16 layers, achieves better accuracy compared to AlexNet, a CNN with 6 layers.https://www.jurnalet.com/jet/article/view/296convolutional neural networkdeep learninggambung clone seriestea clones identification |
| spellingShingle | Ade Ramdan Endang Suryawati R. Budiarianto Suryo Kusumo Hilman F. Pardede Oka Mahendra Rico Dahlan Fani Fauziah Heri Syahrian Deep CNNBased Detection for Tea Clone Identification Jurnal Elektronika dan Telekomunikasi convolutional neural network deep learning gambung clone series tea clones identification |
| title | Deep CNNBased Detection for Tea Clone Identification |
| title_full | Deep CNNBased Detection for Tea Clone Identification |
| title_fullStr | Deep CNNBased Detection for Tea Clone Identification |
| title_full_unstemmed | Deep CNNBased Detection for Tea Clone Identification |
| title_short | Deep CNNBased Detection for Tea Clone Identification |
| title_sort | deep cnnbased detection for tea clone identification |
| topic | convolutional neural network deep learning gambung clone series tea clones identification |
| url | https://www.jurnalet.com/jet/article/view/296 |
| work_keys_str_mv | AT aderamdan deepcnnbaseddetectionforteacloneidentification AT endangsuryawati deepcnnbaseddetectionforteacloneidentification AT rbudiariantosuryokusumo deepcnnbaseddetectionforteacloneidentification AT hilmanfpardede deepcnnbaseddetectionforteacloneidentification AT okamahendra deepcnnbaseddetectionforteacloneidentification AT ricodahlan deepcnnbaseddetectionforteacloneidentification AT fanifauziah deepcnnbaseddetectionforteacloneidentification AT herisyahrian deepcnnbaseddetectionforteacloneidentification |