This competition is organized in conjunction with the International Conference of Frontiers in Handwriting Recognition [ICFHR2022](http://icfhr2022.org/), which will be held in Hyderabad,  India, on December 4-7.

### The competition consists of two tasks: (1) hard classification and (2) soft classification. Each participant can participate in both or only one of them.  Here,  you are competing in TASK 1. To register and compete in [TASK 2](https://www.kaggle.com/competitions/cmhstm22t2), follow this[ link](https://www.kaggle.com/t/3453f441f1f44bb1b9b8008ba832c839).

Automatic script classification has been an active area of research in recent years.  It is essential for understanding, authenticating, and dating historical texts. Script classification is a prerequisite for many historical document processing tasks, such as paleography analysis, writer identification, and handwritten text recognition (HTR).

This competition adds the challenge of classification of medieval Hebrew scripts based on their type and mode.

The task to be evaluated in the present competition is classifying image pages written in Hebrew script. There are 508 pages in the training set that were picked from 125 manuscripts dating from the 10th to 16th centuries. The results will be evaluated on 140 image pages picked from manuscripts that are not included in the training dataset.

In the hard classification task (TASK 1), there is one label for each page image in the data set.


The organizers provide a training data set together with their ground truth in the form of hard labels.