18 datasets found

The dataset used for handwritten text recognition, containing handwritten text images.

A dataset for handwritten text recognition.

A comprehensive handwritten paragraph text recognition system using Vertical Attention Network and Word Beam Search.

Manifold Mixup improves text recognition with CTC loss

The IAM database contains 115,320 isolated and labeled words.

The IAM handwritten database contains 115,320 isolated and labeled words.

The proposed model performs OCR at paragraph level, without any prior segmentation stage.

The USPS dataset consists of 9298 images of handwritten digits 0-9 (10 classes) of 16x16 pixels in gray scale.

The Imgur5K dataset contains 8,094 images, with the handwriting of approximately 5,305 authors published on an online image-sharing and image-hosting service imgur.com.

This work proposes an attention-based sequence-to-sequence model for handwritten word recognition and explores transfer learning for data-efficient training of HTR systems.

Binary images are simple — two possible pixel-valued signals with a single channel. The simplicity of binary images has a significant advantage compared to colored and gray...

A dataset for page segmentation of handwritten historical document images.

A dataset for page segmentation of handwritten historical document images.

A dataset for page segmentation of handwritten historical document images.

A dataset for page segmentation of handwritten historical document images.

A dataset for page segmentation of handwritten historical document images.

A dataset for page segmentation of handwritten historical document images.

A Convolutional Neural Network (CNN) based page segmentation method for handwritten historical document images.