Seeds

Special Issue Information

Dear Colleagues,

The application of imaging and artificial intelligence allows the monitoring of seed quality in an objective, effective, and non-destructive manner. Nowadays, the importance of rapid and non-destructive procedures in seed quality assessment is constantly increasing. Approaches that combine image processing and traditional machine learning or deep learning techniques are often used as an alternative to destructive, time-consuming, subjective, or expensive measurements. Various imaging techniques, such as multispectral and hyperspectral imaging, digital imaging, laser-induced light backscattering imaging, fluorescence imaging, Raman imaging, X-ray computed tomography, magnetic resonance, microwave imaging, or thermal imaging, can be useful to extract information about the external or internal structures of seeds. Image features can provide valuable data about seed characteristics that may be invisible to the naked eye. Selected image features can be used to develop models using different machine learning algorithms to distinguish different seed samples and predict seed quality attributes. These models can be effective at identifying varieties and species of seeds, breeding programs, assessing the effects of cultivation conditions on the seed quality, seed grading and sorting, assessing the effects of storage and processing on seed quality, and detecting seed abnormality, defects, or diseases. Researchers that have dealt with all aspects of the use of imaging and artificial intelligence in seed research are highly encouraged to submit their reviews or research papers.

Dr. Ewa Ropelewska
Dr. Kadir Sabancı
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Seeds is an international peer-reviewed open access quarterly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1000 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

digital imaging
spectral imaging
tomography
thermal imaging
image processing
traditional machine learning
deep learning
seed quality

Published Papers (2 papers)

Download All Papers

Research

Jump to: Review

16 pages, 3569 KiB

Open AccessArticle

Geometric Analysis of Seed Shape Diversity in the Cucurbitaceae

by José Javier Martín-Gómez, Diego Gutiérrez del Pozo, José Luis Rodríguez-Lorenzo, Ángel Tocino and Emilio Cervantes

Seeds 2024, 3(1), 40-55; https://doi.org/10.3390/seeds3010004 - 31 Dec 2023

Cited by 1 | Viewed by 841

Abstract

The Cucurbitaceae is a monophyletic family with close to 1000 species of climbers, including important agronomic species and varieties characterized by tendrils and pepo fruits. The seed’s morphology is varied, and the development and structure of the seed coat have been described in detail on some species. Overall description of the seed shape is based on terms comparing it with geometric figures, but quantitative methods are lacking in the literature. Here we apply a general morphological analysis to seeds of representative genera of the Cucurbitaceae, followed by curvature analysis in the poles and symmetry analysis. These methods are useful for the quantitative description of seed shape and the comparison between species and varieties. Differences between species were found for most morphological measurements, as well as for symmetry and curvature values. The comparison between three species of Cucumis (Cucumis sativus, C. myriocarpus and C. melo) and two varieties of C. melo reveals differences between species and varieties both in curvature and symmetry. The results obtained from both methods, curvature and symmetry analysis, form similar groupings in a cluster analysis. The methods described here were applied for the identification of agronomic varieties and the quantitative description of seed shape in taxonomy. Full article

(This article belongs to the Special Issue Application of Imaging and Artificial Intelligence in Seed Research)

► Show Figures

Figure 1

Review

Jump to: Research

17 pages, 2571 KiB

Open AccessReview

Deep Learning for Soybean Monitoring and Management

by Jayme Garcia Arnal Barbedo

Seeds 2023, 2(3), 340-356; https://doi.org/10.3390/seeds2030026 - 15 Aug 2023

Cited by 1 | Viewed by 1276

Abstract

Artificial intelligence is more present than ever in virtually all sectors of society. This is in large part due to the development of increasingly powerful deep learning models capable of tackling classification problems that were previously untreatable. As a result, there has been a proliferation of scientific articles applying deep learning to a plethora of different problems. The interest in deep learning in agriculture has been continuously growing since the inception of this type of technique in the early 2010s. Soybeans, being one of the most important agricultural commodities, has frequently been the target of efforts in this regard. In this context, it can be challenging to keep track of a constantly evolving state of the art. This review characterizes the current state of the art of deep learning applied to soybean crops, detailing the main advancements achieved so far and, more importantly, providing an in-depth analysis of the main challenges and research gaps that still remain. The ultimate goal is to facilitate the leap from academic research to technologies that actually work under the difficult conditions found in the the field. Full article

(This article belongs to the Special Issue Application of Imaging and Artificial Intelligence in Seed Research)

► Show Figures