# ICFHR2022 Competition - CMHSTM22 - * TASK 1 * — Data

来源：https://www.kaggle.com/competitions/cmhstm22t1/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

##  Dataset description

The participants of this competition will get the only available annotated dataset of Hebrew medieval manuscripts, VML\_HP, which covers major Hebrew script types and modes. The training set contains 508 full manuscript pages picked from 125 manuscripts. The test set consists of 140 image pages picked from the manuscripts that are not present in the training set. Most of the manuscripts used in this dataset are kept in the British Library, the Bibliotheque Nationale de France, and the National Library of Israel.  

-  **To ensure the fairness of the competition, we especially collected a _new_ test set of document images. This new test set is not part of the previous VML_HP releases.**

To simplify the classification task, the selected pages have only one script type and one script mode in the *main text* area. 
The distribution of the script types and modes in the train set is presented in Table 1. 

![](https://i.imgur.com/yh0uB34.jpg)

The participants have to classify the script type of the *main* text area.  The train.zip contains all the images for download.
The file  "train_hard.scv" contains two columns: the first column - ImageID - contains the image name, and the second one is - SCRIPT TYPE - the classification to one of the 14 classes (as illustrated in Figure 1). 

![](https://imgur.com/fcjSiZw.png)

**Figure 1: Ground truth example.**

## Ground truth
To train their models, the participants are provided with a train set accompanied by the corresponding ground
truth file "train_hard.scv". The ground truth includes the image names and the corresponding hard labels (as illustrated in Figure 1). The labels correspond to the *main* text on each page and *ignore* marginal notes. The hard labels are defined according to the 14 classes, which are listed in Table 2.

![](https://imgur.com/eEUFCMT.png)

## Files

*   **train.zip** - the training set images
*   **train_hard.csv** - the training set labels
*   **test.zip** - the test set images (to be released on August 27, 2022)
*   **sample_submission.csv** - a sample submission file in the correct format

## Columns

*   `ImageID` - image name
*   `SCRIPT TYPE` - is a label (one of 14 classes listed in Table 2)