What are some good data augmentation techniques for document images?

问题

I have 1000 resume in png format and I am implementing MaskRcnn for object detection. What data augmentation techniques can I use to improve the mask Rcnn performance?

回答1:

I don't think MaskRCNN or other semantic segmentation or object detection tools are appropriate for this task. Look into OCR libraries such as Tesseract.

来源：https://stackoverflow.com/questions/58748719/what-are-some-good-data-augmentation-techniques-for-document-images