Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

32

DRR
2009

favoriteEmaildiscussreport

93views Document Analysis» more DRR 2009»

Mark Detection from Scanned Ballots

13 years 8 months ago

Mark Detection from Scanned Ballots

Download www.ecse.rpi.edu

Analyzing paper-based election ballots requires finding all marks added to the base ballot. The position, size, shape, rotation and shade of these marks are not known a priori. Scanned ballot images have additional differences from the base ballot due to scanner noise. Different image processing techniques are evaluated to see under what conditions they are able to detect what sorts of marks. Basing mark detection on the difference of raw images was found to be much more sensitive to the mark darkness. Converting the raw images to foreground and background and then removing the form produced better results.

Elisa H. Barney Smith, George Nagy, Daniel P. Lopr

Real-time Traffic

Base Ballot | Document Analysis | DRR 2009 | Images | Raw Images |

claim paper

Related Content

» On Optical MarkSense Scanning

» Ballot mark detection

» Scantegrity II EndtoEnd Verifiability for Optical Scan Election Systems using Invisible In...

» PreElection Testing and PostElection Audit of Optical Scan Voting Terminal Memory Cards

» Robust online modelbased object detection from range images

» Reducing false positive responses in lung nodule detector system by asymmetric adaboost

» Finding Overlapping Communities in Social Networks

» Weakly Supervised Learning of a Classifier for Unusual Event Detection

» Protein Image Alignment via Piecewise Affine Transformations

Post Info
More Details (n/a)

Added	17 Feb 2011
Updated	17 Feb 2011
Type	Journal
Year	2009
Where	DRR
Authors	Elisa H. Barney Smith, George Nagy, Daniel P. Lopresti

Comments (0)