ArUco Markers Cut Android Voting Card Scan Time from 7000ms to Under 140ms
A developer has overhauled the OpenScanVision Android app, replacing its slow QR-plus-edge-detection pipeline with a four-corner ArUco marker-based computer vision system. The original pipeline struggled with unreliable card boundary detection, heavy image processing, and scan times exceeding 7,000 milliseconds on a Samsung A11 device. The new approach places ArUco markers at each card corner, enabling stable position tracking, accurate homography transformation, and consistent perspective correction. This redesign reduced scan processing time to under 140 milliseconds on the same device while improving both QR decoding and OMR bubble detection accuracy. OpenScanVision is built for offline scanning of structured voting cards and uses the device camera to capture, align, and analyze ballot data in real time.
This is an AI-generated summary. ShortSingh links to the original source for the complete article.

Discussion (0)
Log in to join the discussion and vote.
Log in