diff --git a/README.md b/README.md index 5efa87a..455beb9 100644 --- a/README.md +++ b/README.md @@ -23,7 +23,7 @@ pyIMQ for image quality measures is also required and can be found here: https:/ If you prefer to not use the web service, a script can be used for batch processing locally. It can be used to input a set of images and output CSV file with stomata counts, and optionally create heatmaps of each processed image. -Download the pre-trained model weights from here [[Download]](https://drive.google.com/open?id=1StStt1aiN8q1rvSnSVY--87CQ8Z4Pf9b) and unzip the two files (sc_feb2019.caffemodel and sc_feb2019.prototxt). +Download the most current pre-trained model weights from here [[Download]](https://drive.google.com/file/d/18qirGnLD3oEpInyp1KAVf9ZsKf_MQkRb/view?usp=sharing) (alexnetftc_iter_5000_fcn.caffemodel and sc_feb2019.prototxt), or the published model weights here [[Download]](https://drive.google.com/open?id=1StStt1aiN8q1rvSnSVY--87CQ8Z4Pf9b) (sc_feb2019.caffemodel and sc_feb2019.prototxt) and unzip the two files. The processing command allows tweaking various settings such as the input scale and detection threshold. The interface is: diff --git a/templates/about.html b/templates/about.html index a16d10a..377194f 100644 --- a/templates/about.html +++ b/templates/about.html @@ -17,10 +17,11 @@

About

Feel free to contact Karl at karl.fetter [at] gmail.com with questions.

How to Cite

Please cite us if you use this tool for your research. -

Fetter, K.C., Eberhardt, S., Barclay, R.S., Wing, S. and Keller, S.R., 2019. StomataCounter: a neural network for automatic stomata identification and counting. New Phytologist, 223(3), pp.1671-1681. - -

Funding

-

Funding to create Stomata Counter was provided by an NSF grant to Dr. Stephen Keller (Award # 1461868) and a Smithsonian Institution Fellowship to Karl Fetter. +

Fetter, K.C., Eberhardt, S., Barclay, R.S., Wing, S. and Keller, S.R., 2019. StomataCounter: a neural network for automatic stomata identification and counting. New Phytologist, 223(3), pp.1671-1681. + +

Funding

+

Funding to create Stomata Counter was provided by an NSF grant to Dr. Stephen Keller (Award # 1461868) and a Smithsonian Institution Fellowship to Karl Fetter. +

Source Code

The source code for StomataCounter is freely available on GitHub here. Setup requires a cuda8-capable GPU.

{{ super() }} diff --git a/templates/base.html b/templates/base.html index a151b38..e971a2c 100644 --- a/templates/base.html +++ b/templates/base.html @@ -89,7 +89,7 @@

Maintenance on Sat 03/23/2019: We're running some maintenan {% block content %}
{% endblock %} diff --git a/templates/index.html b/templates/index.html index 82173d8..5dc2297 100644 --- a/templates/index.html +++ b/templates/index.html @@ -21,10 +21,13 @@

Stomata Counter

+
+ {{ super() }} +

Welcome to StomataCounter!

-

StomataCounter is a tool to work with plant epidermal micrographs to phenotype stomatal density. Supporting this method is a convolutional neural network trained about about 4,700 micrographs from 700 species of plants. You can read about how StomataCounter was developed and the tests we performed to validate StomataCounter's effectiveness in the preprint. We recommend you register an account with us so that you can return to your jobs after you leave the website.

+

StomataCounter is a tool to work with plant epidermal micrographs to phenotype stomatal density. Supporting this method is a convolutional neural network trained about about 4,700 micrographs from 700 species of plants. You can read about how StomataCounter was developed and the tests we performed to validate StomataCounter's effectiveness in the New Phytologist manuscript. We recommend you register an account with us so that you can return to your jobs after you leave the website.

Instructions for using this site

The simplest way to use StomataCounter is to upload a jpeg using the upload button below, refresh your browser on the Dataset page after a few moments, then export the results using the Dataset operations pulldown menu.

Most users will have several hundred images to measure and uploading zip files of jpegs is more convencient. You can add more zipfiles or individual images to a dataset by navigating to that dataset's page and following the instructions to add more images. Once StomataCounter has finished detecting and counting stomata, you should view the results of all or a set of images to determine how well the method performed. Click on an image to view the result. You should annotate 50 or 100 images (or whatever number you're comfortable with) and view the correlation of human to automatic stomata counts. This is done by clicking on the Dataset operations drop down menu and selecting "Export correlation graph".