00000ctmaa22000003a 4500 UP-1685675941123940356 Buklod 20160908102911.0 aa rb |||1 u| ta 160908s xx d r |||| u| (iLib)UPTAC-00018460478 UPVTC eng LG 993.5 2016 C66 O34 Ocfemia, Danen Clint P. author. CountApPH an application for human-assisted tallying of scanned ballot images from ballot templates used in 2013 Philippine automated elections Danen Clint P. Ocfemia; John D. Ultra, adviser. 2016. [8], 57 leaves illustrations. Undergraduate thesis (B.S. Computer Science) -- University of the Philippines, Tacloban. This research project describes the design and implementation of an application that automatically tallies vote markings in scanned ballot images from ballot templates used in the 2013 Philippine national election. The application can help in conducting risk-limiting election audits to verify election results. Using a scanned ballot image and a corresponding ballot contests template text file as inputs, the application performs a combination of image processing techniques on the ballot image to accurately detect and tally the vote markings in the ballot that represent voter choices. We tested our application on scanned ballot image samples derived from publicly available ballot templates that were used in the 2013 Philippine national election and achieved acceptable accuracy levels. Moreover, since the ballot template design used in the 2016 national election has not significantly changed from its original 2013 design, we are confident that our application would still work with minimal tweaking on ballot templates used in the 2016 national election. Philippine election audit. Ultra, John D. adviser. FI UP UPTAC UPTAC LG 993.5 2016 C66 O34 Thesis