TextCaps Text Recognition Dataset
Date
Publish URL
Paper URL
License
Other

TextCaps is a dataset mainly used for text recognition in images. The dataset contains 28,408 images and 142,040 descriptions. The dataset requires the model to recognize the text in the image to determine where in the text needs to be copied or paraphrased.
Build AI with AI
From idea to launch — accelerate your AI development with free AI co-coding, out-of-the-box environment and best price of GPUs.