Image Data Augmentation

Handwritten OCR augmentation

Introduced by N in Handwritten image augmentation

We are introducing a universal handwritten image augmentation method that is language-agnostic. This groundbreaking technique can be applied to handwritten images in any language worldwide, marking it as the first of its kind. There are four methods for handwritten images which are ThickOCR, ThinOCR, Elongate OCR, Line Erase OCR.

Source: Handwritten image augmentation

Papers


Paper Code Results Date Stars

Tasks


Task Papers Share
Optical Character Recognition (OCR) 1 50.00%
Image Augmentation 1 50.00%

Components


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories