AUTHOR=Qiu Ruicheng , He Yong , Zhang Man 

TITLE=Automatic Detection and Counting of Wheat Spikelet Using Semi-Automatic Labeling and Deep Learning

JOURNAL=Frontiers in Plant Science

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/plant-science/articles/10.3389/fpls.2022.872555

DOI=10.3389/fpls.2022.872555

ISSN=1664-462X

ABSTRACT=The number of wheat spikelets is an important phenotypic trait, can be used to assess the grain yield of the wheat crop. However, manual counting of spikelets is time-consuming and labor-intensive. To develop a cost-effective and high efficient phenotyping system for counting the numbers of spikelets under laboratory conditions, methods were proposed based on imaging processing techniques and deep learning, to accurately detect and count spikelets from color images of wheat spikes captured at the grain filling stage. An unsupervised learning-based method was firstly developed to automatically detect and label spikelets from spike color images and build the datasets for the model training. On the basis of the constructed datasets, a deep convolutional neural network model was retrained using transfer learning to detect the spikelets. Testing results showed that the root mean squared errors, relative root mean squared errors, and the coefficients of determination between the automatic and manual counted spikelets for four wheat lines were 0.62, 0.58, 0.54, and 0.77; 3.96, 3.73, 3.34, and 4.94%; and 0.73, 0.78, 0.84, and 0.67, respectively. We demonstrated that the proposed methods can effectively estimate the numbers of wheat spikelets, which improves the efficiency of wheat spikelets counting and contributes to analyzing the development characteristics of wheat spikes.