Update (18/08/2015) : The final results are available on the result page.
Update (05/05/2015) : Submission are now closed. A competition paper has been submitted to the ICDAR 2015 Competition Chairs, and we will be notified of the review results on the 31st of May (see the competition webpage for more details). Participating teams will then be personally informed of the results and the next steps.
Presentation
This competition aims to motivate research around Super-Resolution (SR) and its application in the specific context of Text Images. Optical Character Recognition (OCR) systems allow one to extract textual information from images. However, when those images lack of resolution, these systems fail. Simple interpolation techniques are very limited at improving the performances. SR approaches aim to enhance the reconstruction process by generating missing details, and are able to provide better shaped images yielding better OCR performances.
A dataset was constructed for this competition in order to evaluate the ability of a given SR system to improve those performances. HR images (High-Resolution) were extracted from French TV video flux, and downsampled by a factor of 2 to create LR images (Low-Resolution). A single frame was extracted for each image (Single Image Super-Resolution). They were manually annotated (transcribed).
The dataset is divided into a training set (training, learning, validation purposes) and a test set :
- The training set contains LR and HR images along with their transcription
- The test set contains only LR images, which are to be Super-Resolved. It was generated by randomly picking 20% of the original images
