Skip to content

Can i use GCN for Information Extraction from a document? #63

Description

@anandh51295

I have a set of images of a id card where i need to extract name and date of birth. for creating a dataset i have converted the set of images to graph for that i have used ocr to get each word and its coordinates. in this each word is the node i have made connection to another node based on direct contact to other node by that i have a graph for all the images i have a graph and to creating a adj matrix i used sparse diagonal matrix of each graph adj matrix. for feature vector at each node i used word2vec at words in each node to create a numpy array. and the labels is the tag that i assigned that could be categorical data. so i want to know that am i doing correct or any changes to be needed...?
thank you

Activity

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

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions