ICDAR'15 Smartphone document capture and OCR competition - challenge 1 (icdar15smartdoc-ch1)

2017-01-11 (v. 1)

Contact author

Joseph Chazalon

University of La Rochelle, France

joseph.chazalon+tc11@univ-lr.fr

003300000000

003300000000


This work is licensed under a Creative Commons Attribution 3.0 Unported License.
You can cite this dataset as: Joseph Chazalon, ICDAR'15 Smartphone document capture and OCR competition - challenge 1 (icdar15smartdoc-ch1) ,1,ID:icdar15smartdoc-ch1_1,URL:http://tc11.cvc.uab.es/datasets/icdar15smartdoc-ch1_1

Dataset Information

Keywords

smartphones, mobile capture, segmentation, object detection, video

Description

Smartphones are replacing personal scanners. They are portable, connected, powerful and affordable. They are on their way to become the new entry point in business processing applications like document archival, ID scanning, check digitization, just to name a few. In order keep our workflows streamlined, we need to make those new capture device as reliable as batch scanners.

We believe an efficient capture process should be able to:

  1. detect and segment the relevant document object during the preview phase;
  2. assess the quality of the capture conditions and help the user improve them;
  3. optionally, trigger the capture at the perfect moment;
  4. and produce a high-quality, controlled output based on the high resolution captured image.

This competition is focused on the first step of this process: efficiently detect and segment document regions, as illustrated by following video showing the ideal output for the preview phase of some acquisition session.

For this challenge, the input will be a set of videoclips containing a document from a predefined set, and the output should be an xml file containing the quadrilateral coordinates in which we can find the document per each frame of the video.

Comments

No comments on this dataset yet.

Add your comment

In order to comment on a dataset you need to be logged on
Register Now!

Valoration

In order to rate this dataset you need to be logged on
Register Now!

ICDAR'15 Smartphone document capture and OCR competition - challenge 1