Form detection and recognition

CascadeTabNet:An Approach for end to end table detection and structure recognition from image-based documents(2020)

Paper
DevashishPrasad/CascadeTabNet

  • Network structure
    Insert picture description here
  • Iterative transfer learning
    uses multi-task learning methods and multiple iterations of transfer learning to achieve goals. First train the model on a general data set, and then fine-tune multiple times for a specific data set.
    Insert picture description here
  • Image Transformation and data augmentation (image transformation and data augmentation)
    • Dilation transform
      In the dilation transform, the original image is first converted into a binary image, and then the original image is transformed to thicken the black pixel area.
    • Smudge transform
      Insert picture description here
  • Pipeline
    Insert picture description here
  • result
    Insert picture description here

Guess you like

Origin blog.csdn.net/studyeboy/article/details/110531299