an automatic computer vision tool
to detect and count parasitic seeds
About
SeedQuant is a seed detection model into an open source software with a user-friendly interface that allows the almost-instantaneous processing and characterization of a single/group of image(s).
With one click, SeedQuant automatically detects and countsgerminated and non-germinated parasitic seeds on images with 95% accuracy.
It simultaneously processes images and extrapolates the germination rate in a generic CSV format, gathering image name and germination rate for further statistics.
SeedQuant can be used on Windows, MacOS, and Linux operating systems.
SeedQuant was developed by Merey Ramazanova and Dr Silvio Giancola for and with the help of Justine Braguy, Dr Muhammad Jamil and Dr Boubacar Kountche.
Witchweeds and broomrapes are root parasitic weeds that represent one of the main threats to global food security. By drastically reducing host crops’ yield, these weeds are responsible for enormous economic losses estimated in billions of dollars annually.
Parasitic plants rely on chemical cues in the rhizosphere, indicating the presence of a host plant in proximity. Using this host dependency, research about parasitic plants focuses on understanding the necessary signals for parasitic seeds germination.
Current studies use germination-based bioassays, where pre-conditioned parasitic seeds are placed in the presence of a chemical or plant root exudates, from which the germination ratio is assessed. Although these protocols are sensitive at the chemical level, the germination recording process is laborious and represents a challenge for researchers.
We propose an automatic seed census tool using computer vision latest development with a deep learning approach for object detection using the algorithm Faster R-CNN to count and discriminate germinated from non-germinated seeds. Our method has shown an accuracy of 95% in counting seeds on completely new images, and reduces the counting time by a significant margin, from 5 min to a fraction of second per image.
We believe that SeedQuant will be of great help for lab bioassays to perform large scale chemicals screening for parasitic seeds applications.
Documentation
To facilitate the use of SeedQuant, we created an extensive manual to guide each user step-by-step from the installation of SeedQuant to its use.
How to open SeedQuant?
How to upload my pictures?
How to automatically detect the seeds on my image(s)?
... and many more questions are carefully answered, supported by screenshots and clear explanations.
We developed a set of annotation files for the pictures of discs containing the seeds of various parasitic plants:
Striga hermontica
Phelipanche aegyptiaca
Phelipanche ramosa and Orobanche cumana
Contact
For plants related matter(s) (type of seeds, protocol, etc), please write to Prof. Salim Al-Babili (salim.albabili@kaust.edu.sa).
For model training and software related matter(s), please contact Prof. Bernard Ghanem (bernard.ghanem@kaust.edu.sa).
Elements
Text
This is bold and this is strong. This is italic and this is emphasized.
This is superscript text and this is subscript text.
This is underlined and this is code: for (;;) { ... }. Finally, this is a link.
Heading Level 2
Heading Level 3
Heading Level 4
Heading Level 5
Heading Level 6
Blockquote
Fringilla nisl. Donec accumsan interdum nisi, quis tincidunt felis sagittis eget tempus euismod. Vestibulum ante ipsum primis in faucibus vestibulum. Blandit adipiscing eu felis iaculis volutpat ac adipiscing accumsan faucibus. Vestibulum ante ipsum primis in faucibus lorem ipsum dolor sit amet nullam adipiscing eu felis.
Preformatted
i = 0;
while (!deck.isInOrder()) {
print 'Iteration ' + i;
deck.shuffle();
i++;
}
print 'It took ' + i + ' iterations to sort the deck.';
