Presentation 2022-03-03
Building a Grape Grain Detection Model for Table Grape Thinning
Chisato Matsumoto, Ko Fujimura,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper addresses the issue of counting grape berries from camera images to support the process of thinning grapes. In the process of deep learning, labeled data is needed to recognize fruit grains, but no data on table grapes is disclosed. Therefore, we constructed the data for this purpose. In addition, using this data, mask R-CNN and Detectron2 were applied and evaluated in comparison with the conventional circle detection method. As a result of the experiment, the method using deep learning obtained higher detection accuracy than the circle detection.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Smart agriculture / table grape thinning / grape detection / deep learning / Mask R-CNN / Detecton2
Paper # LOIS2021-40
Date of Issue 2022-02-24 (LOIS)

Conference Information
Committee LOIS
Conference Date 2022/3/3(1days)
Place (in Japanese) (See Japanese page)
Place (in English) Online
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Toru Kobayashi(Nagasaki Univ.)
Vice Chair Hiroyuki Toda(NTT)
Secretary Hiroyuki Toda(Nagasaki Univ.)
Assistant Kazuki Fukae(Nagasaki Univ.)

Paper Information
Registration To Technical Committee on Life Intelligence and Office Information Systems
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Building a Grape Grain Detection Model for Table Grape Thinning
Sub Title (in English)
Keyword(1) Smart agriculture
Keyword(2) table grape thinning
Keyword(3) grape detection
Keyword(4) deep learning
Keyword(5) Mask R-CNN
Keyword(6) Detecton2
1st Author's Name Chisato Matsumoto
1st Author's Affiliation Otsuma Women's University(Otsuma Women's Univ.)
2nd Author's Name Ko Fujimura
2nd Author's Affiliation Otsuma Women's University(Otsuma Women's Univ.)
Date 2022-03-03
Paper # LOIS2021-40
Volume (vol) vol.121
Number (no) LOIS-401
Page pp.pp.1-6(LOIS),
#Pages 6
Date of Issue 2022-02-24 (LOIS)