Low-computation egocentric barcode detector for the blind
Clement Creusot, Asim Munawar · 2016
Linear barcodes are the principal labeling system for retail products. Barcode reader apps found on smartphones always assume that the localization and framing of the barcode is performed manually by a sighted human operator. This is problematic for visually-impaired people since they don't know where to position the camera to scan the barcode. To solve this problem we propose a hand-free interface to detect barcode using a wearable camera. The user rotate a query product in front of him/her and is informed when and where the barcode is visible. The challenge is to detect small barcodes at arm's length in a video with potentially large motion blur. In this paper we propose a novel technique for barcode detection using very little computation (adapted to wearable systems), presenting very good robustness to blur and size variations, and able to run on HD video streams. The proposed system perform significantly better than the state-of-the-art methods on existing public datasets, while being much faster. A new and challenging egocentric product video dataset is also provided with this paper.