Skip to content

Flow chart recognition using Machine learning. #65738

Answered by arafajs
narayan123411 asked this question in Profile
Discussion options

You must be logged in to vote

Here are a few suggestions for creating a model to recognize and summarize flowchart images:

  1. Use a convolutional neural network (CNN) for image recognition. CNNs are very effective for image classification and object detection in images. You would need a dataset of flowchart images to train the CNN to recognize the different shapes and symbols used in flowcharts.
  2. For the CNN architecture, you could start with a pretrained model like ResNet or VGGNet, then retrain the last layer(s) on your flowchart dataset. This allows the model to leverage features learned from a much larger image dataset.
  3. Each flowchart symbol (rectangle, diamond, arrow etc.) could be treated as a different class label…

Replies: 1 comment 3 replies

Comment options

You must be logged in to vote
3 replies
@michaelkariv
Comment options

@narayan123411
Comment options

@Yogesh7090
Comment options

Answer selected by narayan123411
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment