Automatic leaf shape category discovery

2016 ◽  
Author(s):  
Leonel Olivares ◽  
Jorge Victorino ◽  
Francisco Gomez
Keyword(s):  
Leaf Shape ◽  
Shape Category ◽  
Category Discovery

scholarly journals Correction to: Contour analysis for interpretable leaf shape category discovery

Plant Methods ◽  
2019 ◽  
Vol 15 (1) ◽  
Author(s):  
Jorge Victorino ◽  
Francisco Gómez
Keyword(s):  
Leaf Shape ◽  
Original Version ◽  
Contour Analysis ◽  
Acer Campestre ◽  
Shape Category ◽  
Category Discovery ◽  
Corrected Figure

Unfortunately, the original version of the article [1] contained an error in figure 7. The names of species Umus minor and Acer campestre were interchanged. The corrected figure 7 is given below:

scholarly journals Contour analysis for interpretable leaf shape category discovery

Plant Methods ◽  
2019 ◽  
Vol 15 (1) ◽  
Author(s):  
Jorge Victorino ◽  
Francisco Gómez
Keyword(s):  
Morphological Analysis ◽  
Leaf Shape ◽  
Classification Systems ◽  
Contour Analysis ◽  
Shape Information ◽  
Essential Requirement ◽  
Domain Experts ◽  
Biological Objects ◽  
Shape Category ◽  
Novel Strategy

Abstract Background The categorical description of leaf shapes is of paramount importance in ecology, taxonomy and paleobotanical studies. Classification systems proposed by domain experts support these descriptions. Despite the importance of these visual descriptive systems, classifications based on this expert’s knowledge may be ambiguous or limited when representing shapes in unknown scenarios, as expected for biological exploratory domains. This work proposes a novel strategy to automatically discover the shape categories in a set of unlabeled leaves by only using the leaf-shape information. In particular, we overcome the task of discovering shape categories from different plant species for three different biological settings. Results The proposed method may successfully infer the unknown underlying shape categories with an F-score greater than 92%. Conclusions The approach also provided high levels of visual interpretability, an essential requirement in the description of biological objects. This method may support morphological analysis of biological objects in exploratory domains.

Gemmae in Tetralophozia setiformis (Anastrophyllaceae, Marchantiophyta) and their second record in Eurasia

2017 ◽  
Vol 51 ◽  
pp. 242-250
Author(s):  
M. V. Dulin
Keyword(s):  
British Columbia ◽  
Asexual Reproduction ◽  
Leaf Shape ◽  
Leaf Size ◽  
Komi Republic ◽  
The Other ◽  
Widespread Species ◽  
Northern Urals ◽  
Sexual And Asexual Reproduction ◽  
Murmansk Region

Tetralophozia setiformis is a widespread species occurring usually without organs of sexual and asexual reproduction. Gemmae of Tetralophozia setiformis were observed for the second time in Russia and Eurasia in the Northern Urals, Komi Republic. They form compact masses over upper leaves. The compact masses consist largely (70 %) of immature gemmae. Description of gemmae and gemmiparous shoots from the Northern Urals and their comparison with those from the other known localities, namely British Columbia (Canada) and the Murmansk Region (European Russia) were carried out. The gemmiparous plants of T. setiformis from the Northern Urals have approximately the same width as plants without gemmae but they are shorter. The leaves of gemmiparous plants from the Northern Urals are similar to leaves of gemmiparous plants from British Columbia. The leaf shape in upper part of the gemmiparous shoots varies from the typical to ± modified from gemmae production. These leaf shape transitions include reduction of leaf size and lobe number from 4 to 2–3, suppression of development and disappearance of characteristic teeth at the base of sinus. Gemmae size (17 × 22 μm) of plants from the Northern Urals is within variability recorded for plants from the Murmansk Region and British Columbia.

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

2021 ◽  
Vol 8 (1) ◽  
Author(s):  
Yanping Zhang ◽  
Jing Peng ◽  
Xiaohui Yuan ◽  
Lisi Zhang ◽  
Dongzi Zhu ◽  
...  
Keyword(s):  
Prunus Avium ◽  
Cultivar Identification ◽  
Leaf Shape ◽  
Persistent Homology ◽  
Growth Period ◽  
Image Features ◽  
Crop Species ◽  
Score Level Fusion ◽  
Level Fusion ◽  
Leaf Image

AbstractRecognizing 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.

scholarly journals Apple Autotetraploids with Enhanced Resistance to Apple Scab (Venturia inaequalis) Due to Genome Duplication-Phenotypic and Genetic Evaluation

2021 ◽  
Vol 22 (2) ◽  
pp. 527
Author(s):  
Małgorzata Podwyszyńska ◽  
Monika Markiewicz ◽  
Agata Broniarek-Niemiec ◽  
Bożena Matysiak ◽  
Agnieszka Marasek-Ciolakowska
Keyword(s):  
Venturia Inaequalis ◽  
Leaf Shape ◽  
Apple Scab ◽  
Early Period ◽  
Physiological Parameters ◽  
Aflp Analysis ◽  
Poor Growth ◽  
Enhanced Resistance ◽  
Apple Cultivars ◽  
Old Trees

Among the fungal diseases of apple trees, serious yield losses are due to an apple scab caused by Venturia inaequalis. Protection against this disease is based mainly on chemical treatments, which are currently very limited. Therefore, it is extremely important to introduce cultivars with reduced susceptibility to this pathogen. One of the important sources of variability for breeding is the process of polyploidization. Newly obtained polyploids may acquire new features, including increased resistance to diseases. In our earlier studies, numerous tetraploids have been obtained for several apple cultivars with ‘Free Redstar’ tetraploids manifesting enhanced resistance to apple scab. In the present study, tetraploids of ‘Free Redstar’ were assessed in terms of phenotype and genotype with particular emphasis on the genetic background of their increased resistance to apple scab. Compared to diploid plants, tetraploids (own-rooted plants) were characterized with poor growth, especially during first growing season. They had considerably shorter shoots, fewer branches, smaller stem diameter, and reshaped leaves. In contrast to own-rooted plants, in M9-grafted three-year old trees, no significant differences between diplo- and tetraploids were observed, either in morphological or physiological parameters, with the exceptions of the increased leaf thickness and chlorophyll content recorded in tetraploids. Significant differences between sibling tetraploid clones were recorded, particularly in leaf shape and some physiological parameters. The amplified fragment length polymorphism (AFLP) analysis confirmed genetic polymorphism of tetraploid clones. Methylation-sensitive amplification polymorphism (MSAP) analysis showed that the level of DNA methylation was twice as high in young tetraploid plants as in a diploid donor tree, which may explain the weaker vigour of neotetraploids in the early period of their growth in the juvenile phase. Molecular analysis showed that ‘Free Redstar’ cultivar and their tetraploids bear six Rvi genes (Rvi5, Rvi6, Rvi8, Rvi11, Rvi14 and Rvi17). Transcriptome analysis confirmed enhanced resistance to apple scab of ‘Free Redstar’ tetraploids since the expression levels of genes related to resistance were strongly enhanced in tetraploids compared to their diploid counterparts.

scholarly journals The Preferences of Different Cultivars of Lettuce Seedlings (Lactuca sativa L.) for the Spectral Composition of Light

Agronomy ◽  
2021 ◽  
Vol 11 (6) ◽  
pp. 1211
Author(s):  
Barbara Frąszczak ◽  
Monika Kula-Maximenko
Keyword(s):  
Chlorophyll Content ◽  
Blue Light ◽  
White Light ◽  
Leaf Shape ◽  
Red Light ◽  
Spectral Composition ◽  
Fresh Weight ◽  
Light Spectrum ◽  
Dark Green ◽  
Relative Chlorophyll Content

The spectrum of light significantly influences the growth of plants cultivated in closed systems. Five lettuce cultivars with different leaf colours were grown under white light (W, 170 μmol m−2 s−1) and under white light with the addition of red (W + R) or blue light (W + B) (230 μmol m−2 s−1). The plants were grown until they reached the seedling phase (30 days). Each cultivar reacted differently to the light spectrum applied. The red-leaved cultivar exhibited the strongest plasticity in response to the spectrum. The blue light stimulated the growth of the leaf surface in all the plants. The red light negatively influenced the length of leaves in the cultivars, but it positively affected their number in red and dark-green lettuce. It also increased the relative chlorophyll content and fresh weight gain in the cultivars containing anthocyanins. When the cultivars were grown under white light, they had longer leaves and higher value of the leaf shape index. The light-green cultivars had a greater fresh weight. Both the addition of blue and red light significantly increased the relative chlorophyll content in the dark-green cultivar. The spectrum enhanced with blue light had positive influence on most of the parameters under analysis in butter lettuce cultivars. These cultivars were also characterised by the highest absorbance of blue light.

Sign in / Sign up

Export Citation Format

Share Document