Automatic Labelling to the rescue
Challenge: When we started the computer vision model that can identify objects in an image and video, we never realized that the objects, we need to identify may take us over a year to label. We needed to label thousands of objects in millions of images to train our model. Innovation is the mother of necessity and we was forced to come up with options to automate our instrument labeling task.
We could not use solutions from companies such as https://thehive.ai/ as those label objects in rectangle boxes and we needed label exact boundaries of instruments.
Solution:
We analyzed multiple tools which could help us in reducing the time and cost of labeling. The following are the tools which were evaluated:
Based on our selection criteria,3-4 seconds for labeling, we selected Labelme. Once selected, we needed to select a model which can help in automating the labeling of objects. Among various options below, we selected Detectron2.
From that point onwards, it was easy for us to build a pipeline that can run while we work on other things. This approach allowed us to finish the labeling task in a week.
Results and Learning:
Our automatic labelling solution is available now to all our customers at no charge for the models which we are developing. In case you have any query on how to auto-label the images, please contact us for more information at sales@nextgeninvent.com.
Visit our website at www.nextgeninvent.com
