Authors: Yuhao Zhou
Identifier: CSBE22114
Download file:
Published in: CSBE-SCGAB Technical Conferences » AGM Charlottetown 2022

Download RAW file:
Description: The understanding of rice yield traits can effectively promote the techniques of breeding, including the measurement of panicle length, panicle width, total spikelets number, filled spikelets number, and thousand grain weight. However, current equipment can only achieve measuring rice grains, and researchers still need to spend a lot of energy on rice threshing. In this study, a measurement method of whole panicle feeding of rice is proposed, which can be used to obtain automatically rice yield traits. In this method, the whole panicle of rice is threshed for a long time, so as to ensure that the whole panicle is completely removed. Then, the separated rice grains are measured relying on the existing technology, and the threshed panicles are counted by using the deep learning technology. Finally, the computer program integrates the two sets of data to obtain the rice yield traits. Because the process of measuring rice yield traits only needs to count the number of empty particles, the error caused by this method can be ignored. This method can effectively reduce the workload of scientific researchers, and also provides a new direction for the development of measuring technology, which applies to rice yield traits.

Keywords: whole panicle,measure,rice yield traits,deep learning
Pages -
Date: 2022-07-24
Technical field:
Conference name: CSBE/SCGAB 2022 Annual Conference, Charlottetow, PEI, 24-27 July 2022.
Session name: Food and Bioprocessing1

Other information:
Type: Text.Abstract
Publication type: Presentation
Coverage: China, People's Republic of
Language 1: en
Language 2:
Rights: Canadian Society for Bioengineering
Other files: