Correction to: Detection and analysis of wheat spikes using convolutional neural networks (Plant Methods (2018) 14 (100) DOI: 10.1186/s13007-018-0366-8)

Abstract

In the original publication of this article [1] the authors stated that important resources would be made available online to readers. Unfortunately, due to an error on the authors' behalf, a link to those resources was not included in the final version of the manuscript. The SPIKE dataset, including images of wheat spikes and labelled bounding boxes for individual spikes, as well as the four trained CNN models described in the article, can now be found at the following sourceforge page: https ://sourc eforg e.net/proje cts/spike -datas et/ The link provides access to the free download of all images used in the article as well as their ground truth labelling. The four CNN models available for download at the sourceforge link are to be used in conjunction with the microsoft cognitive toolkit, available at: https ://docs.micro soft.com/en-gb/cogni tive-toolk it/ Finally, an additional more user-friendly program has also been uploaded to the sourceforge page. This program contains the same functionality as is currently avail able through the cognitive toolkit. However, the user willbe able to quickly and easily select a dataset of their own images and run the models for spike detection, without downloading and installing the cognitive toolkit.