Automatic morphology phenotyping of tetra- and hexaploid wheat spike using computer vision methods

Image-based classification of wheat spikes by glume pubescence using convolutional neural networks

Introduction

Pubescence is an important phenotypic trait observed in both vegetative and generative plant organs. Pubescent plants demonstrate increased resistance to various environmental stresses such as drought, low temperatures, and pests. It serves as a significant morphological marker and aids in selecting stress-resistant cultivars, particularly in wheat. In wheat, pubescence is visible on leaves, leaf sheath, glumes and nodes. Regarding glumes, the presence of pubescence plays a pivotal role in its classification. It supplements other spike characteristics, aiding in distinguishing between different varieties within the wheat species. The determination of pubescence typically involves visual analysis by an expert. However, methods without the use of binocular loupe tend to be subjective, while employing additional equipment is labor-intensive. This paper proposes an integrated approach to determine glume pubescence presence in spike images captured under laboratory conditions using a digital camera and convolutional neural networks.

Methods

Initially, image segmentation is conducted to extract the contour of the spike body, followed by cropping of the spike images to an equal size. These images are then classified based on glume pubescence (pubescent/glabrous) using various convolutional neural network architectures (Resnet-18, EfficientNet-B0, and EfficientNet-B1). The networks were trained and tested on a dataset comprising 9,719 spike images.

Results

For segmentation, the U-Net model with EfficientNet-B1 encoder was chosen, achieving the segmentation accuracy IoU = 0.947 for the spike body and 0.777 for awns. The classification model for glume pubescence with the highest performance utilized the EfficientNet-B1 architecture. On the test sample, the model exhibited prediction accuracy parameters of F1 = 0.85 and AUC = 0.96, while on the holdout sample it showed F1 = 0.84 and AUC = 0.89. Additionally, the study investigated the relationship between image scale, artificial distortions, and model prediction performance, revealing that higher magnification and smaller distortions yielded a more accurate prediction of glume pubescence.

Scientific support to plant breeding and seed production in Siberia in the XXI century

Agriculture in the Russian Federation is fundamental to the country’s economic performance, living standards, the wellbeing of people and state safety. Considerations relating to food security, prospects of and challenges before plant breeding in the Siberian Federal District (SFD), the largest agricultural area of the Russian Federation, are provided in the article. The agricultural area used in the SFD is about 50 million hectares and accounts for 13 % of the country’s gross grain production. The need for the introduction of modern molecular biological methods, bioengineering and IT technology is demonstrated and discussed. As Russia as a whole, Siberia is largely engaged in unpromising extensive farming practices, which rely on natural soil fertility, and this factor should be taken into account. Another issue is noncompliance with intensive farming technologies used for cultivating new-generation commercial cultivars. Although capital investments in plant breeding are the most cost effective investments in crop production, breeders’ efforts remain underfunded. The article explains the need for fundamental reform in this economic sector: the recognition of plant breeding as being a fundamental science; a fair increase in its funding; the development of a breeding strategy, nationally and regionally; the further expansion of the network of the Breeding Centers; the re-establishment and improvement of the universities’ departments specialized in plant breeding and seed production; having more state-funded places in the universities for training plant breeders to be able to maintain and cement the country’s advanced position in plant breeding and to develop new globally competitive next-generation cultivars of main crops. Should these issues be ignored, all the problems that have accumulated to date will lead to risks of long-term instability in this economic sector. The need for the careful preservation of continuity in plant breeders and plants being bred is stated. The regulatory functions of the state and agricultural science in plant breeding, plant industry and seed production are considered.