Construction of apricot variety search engine based on deep learning  

作　　者：Chen Chen Lin Wang Huimin Liu Jing Liu Wanyu Xu Mengzhen Huang Ningning Gou Chu Wang Haikun Bai Gengjie Jia Tana Wuyun 

机构地区：[1]State Key Laboratory of Tree Genetics and Breeding,Research Institute of Non-timber Forestry,Chinese Academy of Forestry,Zhengzhou,Henan 450003,China [2]Shenzhen Branch,Guangdong Laboratory of Lingnan Modern Agriculture,Genome Analysis Laboratory of the Ministry of Agriculture and Rural Affairs,Agricultural Genomics Institute at Shenzhen,Chinese Academy of Agricultural Sciences,Shenzhen,Guangdong 518120,China [3]Kernel-Apricot Engineering and Technology Research Center of State Forestry and Grassland Administration,Zhengzhou,Henan 450003,China [4]Key Laboratory of Non-timber Forest Germplasm Enhancement and Utilization of National Forestry and Grassland Administration,Zhengzhou,Henan 450003,China

出　　处：《Horticultural Plant Journal》2024年第2期387-397,共11页园艺学报（英文版）

基　　金：supported by the Fundamental Research Funds for the Central Non-profit Research Institution of the Chinese Academy of Forestry (Grant No.CAFYBB2020ZY003);the Key S&T Project of Inner Mongolia (Grant No.2021ZD0041-001-002);the Central Public-interest Scientific Institution Basal Research Fund (Grant No.11024316000202300001)。

摘　　要：Apricot has a long history of cultivation and has many varieties and types. The traditional variety identification methods are timeconsuming and labor-consuming, posing grand challenges to apricot resource management. Tool development in this regard will help researchers quickly identify variety information. This study photographed apricot fruits outdoors and indoors and constructed a dataset that can precisely classify the fruits using a U-net model (F-score:99%), which helps to obtain the fruit's size, shape, and color features. Meanwhile, a variety search engine was constructed, which can search and identify variety from the database according to the above features. Besides, a mobile and web application (ApricotView) was developed, and the construction mode can be also applied to other varieties of fruit trees.Additionally, we have collected four difficult-to-identify seed datasets and used the VGG16 model for training, with an accuracy of 97%, which provided an important basis for ApricotView. To address the difficulties in data collection bottlenecking apricot phenomics research, we developed the first apricot database platform of its kind (ApricotDIAP, http://apricotdiap.com/) to accumulate, manage, and publicize scientific data of apricot.

关 键 词：APRICOT VARIETY Convolutional neural network Deep learning Database platform Mobile application Image retrieval 

分 类 号：S662.2[农业科学—果树学]