Deep transfer learning based photonics sensor for assessment of seed-quality

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F62690094%3A18450%2F22%3A50019103" target="_blank" >RIV/62690094:18450/22:50019103 - isvavai.cz</a>

Result on the web

<a href="https://linkinghub.elsevier.com/retrieve/pii/S0168169922002083" target="_blank" >https://linkinghub.elsevier.com/retrieve/pii/S0168169922002083</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.compag.2022.106891" target="_blank" >10.1016/j.compag.2022.106891</a>

Result language

angličtina

Original language name

Deep transfer learning based photonics sensor for assessment of seed-quality

Original language description

Seed-quality is one of the most important factors for achieving the objectives of uniform seedling establishment and high crop yield. In this work, we propose laser backscattering and deep transfer learning (TL) based photonics sensor for automatic identification and classification of high-quality seeds. The proposed sensor is based on capturing a single backscattered image of a seed sample and processing the acquired images by using deep learning (DL) based algorithms. Advantages of the proposed sensor include its ability to characterize morphological and biological changes related to seed-quality, lower memory requirement, robustness against external noise and vibration, easy alignments, and low complexity of acquisition and processing units. Furthermore, use of DL based processing frameworks including convolution neural network (CNN) and various TL models (VGG16, VGG19, InceptionV3, and ResNet50) extract abstract features from the images without any additional image processing and accelerate classification efficiency. Obtained results indicate that all the DL models performed significantly well with higher accuracy; however, InceptionV3 outperformed rest of the models with accuracy reaching up to 98.31%. To validate performance of the proposed sensor standard quality parameters comprising percentage imbibition (PI), radicle length, and germination percentage (GP) were also calculated. Significant change (p &lt; 0.05) in these parameters show that the proposed sensor can accurately monitor the quality of seeds with higher accuracy. Moreover, experimental simplicity and DL based automatic classification make the sensor suitable for real-time applications. © 2022 Elsevier B.V.

Czech name

—

Czech description

—

Type

J_imp - Article in a specialist periodical, which is included in the Web of Science database

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

—

Continuities

S - Specificky vyzkum na vysokych skolach

Publication year

2022

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Name of the periodical

Computers and Electronics in Agriculture

ISSN

0168-1699

e-ISSN

1872-7107

Volume of the periodical

196

Issue of the periodical within the volume

May

Country of publishing house

GB - UNITED KINGDOM

Number of pages

10

Pages from-to

"Article number: 106891"

UT code for WoS article

000806136800007

EID of the result in the Scopus database

2-s2.0-85127225551