SeedQuant: A Deep Learning-based Census Tool for Seed Germination of Root Parasitic Plants

الموضوعات

علوم تطبيقية وتكنولوجية

الملخص

Witchweeds and broomrapes are root parasitic weeds that represent one of the mainthreats to global food security. By drastically reducing host crops' yield, the parasitesare often responsible for enormous economic losses estimated in billions of dollarsannually. Parasitic plants rely on a chemical cue in the rhizosphere, indicating thepresence of a host plant in proximity. Using this host dependency, research in parasiticplants focuses on understanding the necessary triggers for parasitic seeds germination,to either reduce their germination in presence of crops or provoke germinationwithout hosts (i.e. suicidal germination). For this purpose, a number of syntheticanalogs and inhibitors have been developed and their biological activities studied onparasitic plants around the world using various protocols. Current studies are usinggermination-based bioassays, where pre-conditioned parasitic seeds are placed in thepresence of a chemical or plant root exudates, from which the germination ratio isassessed. Although these protocols are very sensitive at the chemical level, the germinationrate recording is time consuming, represents a challenging task for researchers,and could easily be sped up leveraging automated seeds detection algorithms. In orderto accelerate such protocols, we propose an automatic seed censing tool usingcomputer vision latest development. We use a deep learning approach for object detectionwith the algorithm Faster R-CNN to count and discriminate germinated fromnon-germinated seeds. Our method has shown an accuracy of 95% in counting seedson completely new images, and reduces the counting time by a signi cant margin,from 5 min to a fraction of second per image. We believe our proposed software \SeedQuant" will be of great help for lab bioassays to perform large scale chemicalsscreening for parasitic seeds applications.

روابط وملفات

التعريف والنوع

رقم الوثيقة

ff8d4bb3-ee8f-4f8c-99d2-632221a9108a

رقم العقد

0

نوع الوسائط

Crawler

نوع المحتوى

الرسائل العلمية

صيغة المصدر

رسائل ماجيستير

نوع الملف

pdf image

أسماء الملفات

ff8d4bb3-ee8f-4f8c-99d2-632221a9108a_1.pdf

بيانات النشر

ألقاب المؤلفين

[{"name_ar":" Merey Ramazanova","title_ar":"اعداد","title_en":"Preparation"},{"name_ar":"Bernard Ghanem","title_ar":"اشراف","title_en":"Supervision"}]

اللغة

English

المصدر والدورية

اسم المصدر

SeedQuant: A Deep Learning-based Census Tool for Seed Germination of Root Parasitic Plants

المحتوى والصفحات

عدد الصفحات

0

كلمات الباحثين

computer vision census tool seed counting deep learning

إشراف وإعداد

الإشراف

Bernard Ghanem

الإعداد

Merey Ramazanova

الاقتباسات الببليوغرافية