Introduction
Handwriting recognition is an open research topic in the document analysis community. We provide two new, freely available real world datasets for an established problem. The competition consists of two independent tasks, namely segmented single Arabic digits and Arabic digit strings. Contributions will be accepted for either of the competitions. The dataset of segmented digits is a subset of the larger dataset of digit strings. It has been collected mostly amongst students of the Vienna University of Technology and consists of about 300 writers, female and male alike. To our knowledge, this database is the first one to provide files as RGB. They are delivered in original size with a resolution of 300 dpi. Contrary to other datasets, the digits are not size-normalized, but provided in the original size since in real world cases, the writers’ styles include variation in size as well as writing style.
We invite all Researchers in the field of Digit and Digit String Recognition for participating to the contest which is organized in conjunction with ICDAR 2013. The evaluation and a short abstract of the submitted methods will be presented at ICDAR 2013 and published in conference proceedings. All rights of the submitted software remain by the authors.
Due to the low number of participants in the Handwritten Digit String Competition, only the competition for the Single Handwritten Digits have been carried out in conjunction with ICDAR 2013. We plan to organize the Handwritten Digit String Competition in conjunction with upcomping conferences.
Registration
In order to register, please send an e-mail to hdrc@cvl.tuwien.ac.at until 11.03.2013 18.03.2013 including:
- Subject: [ICDAR2013-HDRC]
- Author names and affiliation
- Short description of the method submitted
- References of the method submitted, if available
Competition Mode
Contributions will be accepted as binaries. The input will be an RGB image (300 dpi, not size-normalized), the output is required to be the recognized ASCII character or character string respectively. For segmented digits, first and second guess will be evaluated.
Participants can apply either for the Digit Recognition or the Digit String Recognition Competition. The database of segmented digits consists of 10 classes (0-9), with roughly 4000 samples per class. These digits are a subset of the digit string database, where only unconnected digits were extracted. Similar to the digit string database, the training set consists of randomly selected digits. When setting up the database, a uniform distribution of the occurrences of each digit was ensured.
- Digit Recognition
-
Specification of the executable:
DigitRec arg1 arg2
arg1 – the input RGB image (single digit)
arg2 – text file with the result (first guess,second guess)
- Digit String Recognition
-
Specification of the executable:
DigitRec arg1 arg2
arg1 – the input RGB image (digit string)
arg2 – text file with the recognized digit string
Datasets
The CVL Single Digit dataset consists of 7000 single digits (700 digits per class) written by approximately 60 different writers. The validation set has the same size but different writers. The validation set may be used for parameter estimation and validation but not for supervised training. The CVL Digit Strings dataset uses 10 different digit strings from a total of about 120 writers resulting in 1262 training images. The digits from the CVL Single Digit dataset were extracted from these strings.
Terms of Use and Citation Request
This database may be used for non-commercial research purpose only. If you publish material based on this database, we request you to include a reference to:
Markus Diem, Stefan Fiel, Angelika Garz, Manuel Keglevic, Florian Kleber and Robert Sablatnig, ICDAR 2013 Competition on Handwritten Digit Recognition (HDRC 2013), In Proc. of the 12th Int. Conference on Document Analysis and Recognition (ICDAR) 2013, pp. 1454-1459, 2013.
File Naming
The numbers before the first minus are the respective class labels succeeded by an unique ID.
- 2-0202-21-04.png is an image that contains a single digit with groundtruth 2
- 135579-0001-10.png is an image that contains the digit string 135579
Schedule
- Registration to the contest: 11.03.2013 18.03.2013
- Submission of the required executable: 31.03.2013
Organizers
Contact
Robert Sablatnig, CVL, Vienna University of Technology:
e-mail: hdrc@cvl.tuwien.ac.at
CVL Digit Database is licensed under a Creative Commons Attribution-NonCommercial 3.0 Unported License.