Call for Participation
|
ID |
Competition Title |
Link |
A short description |
1 |
ICFHR2012 Competition on Recognition of Online Handwritten Mathematical Expressions (CROHME-II) |
... |
|
2 |
ICFHR2012 Handwritten Document Image Binarisation Contest (H-DIBCO 2012) |
Document image binarization is an important step in the document image analysis and recognition pipeline. In this respect, it is imperative to have a benchmarking dataset along with an objective evaluation methodology to capture the efficiency of current document image binarization methodologies. Following the success of DIBCO series (DIBCO 2009 organised in conjunction with ICDAR’09, H-DIBCO 2010 organized in conjunction with ICFHR 2010 and DIBCO 2011 organised in conjunction with ICDAR’11) the follow-up of this contest is organised in conjuction with ICFHR 2012. In H-DIBCO 2012 (Handwritten Document Image Binarization Contest), the general objective is to record recent advances in handwritten document image binarization using established evaluation performance measures. The benchmarking dataset that will be used in the contest will augment the existing dataset of the DIBCO series containing handwritten document images that are representative of the potential problems which are challenging in the binarization process. All researchers in the field of Document Image Binarization are invited to register and participate in H-DIBCO 2012. An agreement will be signed by the participants and the organizers in order to protect the Intellectual Property Rights (IPR) of the submitted software. The description of the methods and the evaluation scores will be presented during a dedicated ICFHR 2012 session. A report on the competition will be published in the ICFHR 2012 conference proceedings. At the end of the competition, the testing dataset along with the required program to run the evaluation measures will become publicly available. |
|
3 |
ICFHR2012 On-Line Arabic Handwriting Recognition Competition (OAHRC 2012) |
... |
|
4 |
ICFHR2012 Competition on Forensic Signature Verification (4NSigComp2012) |
Our scenario aims at a comparison between FHEs opinions on authorship of signatures and the systems performances to detect skilled forgeries (simulated and disguised signatures) from genuine signatures of a reference writer. This time, we will use more data than in 2010 to make the outcomes more significant. The training set will be all data from the 4NSigComp2010 competition. The evaluation dataset will consist of 501 images, containing 51 reference signatures from three authors and 450 questioned signatures. For evaluation we will apply analysis methods used by FHEs to assess the value of the evidence, i.e., we will take the likelihood ratios more into account than in previous competitions. We will build our evaluation on the framework FoCal which can be found at the site of Niko Brummer and calculate the Cllr-Score. Participants of both academia and industry are invited to enter the competition. Organizers of this event will not participate in the competition. Participants can participate anonymous and/or they can choose to be anonymous in publications. Participants should email Marcus Liwicki (Marcus.Liwicki@dfki.de) to join the competition. |
|
5 |
ICFHR2012 Word Spotting Competition |
Handwritten word spotting is the task of detecting query words in handwritten document image collections without involving a traditional OCR procedure. We invite all researchers in the field of handwritten document analysis and recognition to register and participate in the ICFHR 2012 Word Spotting Competition. The general objective of this contest is to evaluate recent query-by example retrieval approaches for handwritten word spotting. According to these approaches, a query word image as well as a set of handwritten document images are provided as input. The output consists of a subset of the initial set of images as well as the corresponding bounding box coordinates for each spotted word instance. In the context of the competition, a benchmarking dataset will be built along with an evaluation platform in order to test and compare recent algorithms for handwritten word spotting in realistic circumstances. |
|
6 |
ICFHR2012 Writer Identification Contest |
Writer identification is important for forensic analysis, helping experts to deliberate on the authenticity of documents. Following the successful organization of two writer identification contests in the framework of ICDAR 2011, we organize the ICFHR 2012 Writer Identification Contest in order to record recent advances in the field of writer identification. This contest is set up around two challenges mainly differing in the involved scripts. We invite all researchers in the field of writer identification to register and participate in the ICFHR 2012 Writer Identification Contest. Although participants can choose to compete in any of these challenges, they are strongly encouraged to compete in both of them. This will allow us to perform meaningful comparisons, while it only involves minimal effort from the participants. For more information, please visit the individual challenge websites. |
|
7 |
ICFHR2012 French Handwriting Recognition Competition |
Following the success of the ICDAR 2011 French handwriting recognition competition, we are pleased to invite all researchers in the field of off-line handwriting processing to participate in the new ICFHR2012 French handwriting recognition competition. Two recognition tasks of rising difficulties are proposed: the first one corresponds to the recognition of snippets of words with the help of a given dictionary and the second one consists in recognizing blocks of words segmented into lines. The database used is part of the high-quality RIMES database composed of mails sent by individuals to companies or administrations. |
