Chapter

Camera-Based Document Analysis and Recognition

Volume 7139 of the series Lecture Notes in Computer Science pp 29-41

A Head-Mounted Device for Recognizing Text in Natural Scenes

  • Carlos Merino-GraciaAffiliated withLancaster UniversityNeurochemistry and Neuroimaging Laboratory, University of La Laguna
  • , Karel LencAffiliated withLancaster UniversityCenter for Machine Perception, Czech Technical University
  • , Majid MirmehdiAffiliated withCarnegie Mellon UniversityVisual Information Laboratory, University of Bristol

* Final gross prices may vary according to local VAT.

Get Access

Abstract

We present a mobile head-mounted device for detecting and tracking text that is encased in an ordinary flat-cap hat. The main parts of the device are an integrated camera and audio webcam together with a simple remote control system, all connected via a USB hub to a laptop. A near to real-time text detection algorithm (around 14 fps for 640×480 images) which uses Maximal Stable Extremal Regions (MSERs) for image segmentation is proposed. Comparative text detection results against the ICDAR 2003 text locating competition database along with performance figures are presented.

Keywords

wearable device text detection text understanding MSER