MFCIS: an automatic leaf-based identification pipeline for plant cultivars using deep learning and persistent homology

Abstract

Recognizing plant cultivars reliably and efficiently can benefit plant breeders in terms of property rights protection and innovation of germplasm resources. Although leaf image-based methods have been widely adopted in plant species identification, they seldom have been applied in cultivar identification due to the high similarity of leaves among cultivars. Here, we propose an automatic leaf image-based cultivar identification pipeline called MFCIS (Multi-feature Combined Cultivar Identification System), which combines multiple leaf morphological features collected by persistent homology and a convolutional neural network (CNN). Persistent homology, a multiscale and robust method, was employed to extract the topological signatures of leaf shape, texture, and venation details. A CNN-based algorithm, the Xception network, was fine-tuned for extracting high-level leaf image features. For fruit species, we benchmarked the MFCIS pipeline on a sweet cherry (Prunus avium L.) leaf dataset with >5000 leaf images from 88 varieties or unreleased selections and achieved a mean accuracy of 83.52%. For annual crop species, we applied the MFCIS pipeline to a soybean (Glycine max L. Merr.) leaf dataset with 5000 leaf images of 100 cultivars or elite breeding lines collected at five growth periods. The identification models for each growth period were trained independently, and their results were combined using a score-level fusion strategy. The classification accuracy after score-level fusion was 91.4%, which is much higher than the accuracy when utilizing each growth period independently or mixing all growth periods. To facilitate the adoption of the proposed pipelines, we constructed a user-friendly web service, which is freely available at http://www.mfcis.online.

Cerasus Humilis Cultivars Identification With Small-Sample and Unbalanced Dataset Based on Efficient Net-B0+ranger Networks

“…Although leaf image-based methods have been widely adopted in plant species identification. Zhang et al (2021) proposed an Xception network to identify 88 sweet cherry cultivars and 100 soybean cultivars under controlled conditions, with an accuracy of 83.52% and 91.4%, respectively. Liu et al (2020) proposed an efficient and convenient method for the classification of 14 apple cultivars with a sample background using a deep convolutional neural network and achieved an overall accuracy of 97.11%.…”

Multi-Information Model for Large-Flowered Chrysanthemum Cultivar Recognition and Classification

“…In terms of dynamic phenotypic identification, good progress has been made in related studies on leaves. By obtaining leaf images at different growth stages ( Zhang et al, 2021 ) or under different stress conditions ( Hao et al, 2020 ), researchers have established a classification model that can recognize the changing leaves through multi-feature or multi-scale input. However, compared to leaf images, flowers are only available during a short period of the year.…”

A Review of Plant Phenotypic Image Recognition Technology Based on Deep Learning

“…(1) the basic idea of relational structure matching method for PPIR is shown in Figure 1 [22]. In this method, first, the input images are preprocessed in order to extract features, while using multi-scale curvature space to describe the geometric features, as well as the fuzzy particle swarm algorithm and genetic algorithm.…”

“…Figure 3 shows its basic idea. Feature extraction involving the extraction of shape, texture, color, and other major feature information is an important step in PPIR [22]. In shape based feature learning, edge detection and shape context description methods are widely used in order to extract the plant contours from the input images to achieve plant recognition [19].…”