Work

Text recognition approaches for indoor robotics: a comparison

Year: 2014

Type: conference-paper

Abstract: This paper evaluates the performance of different text recognition techniques for a mobile robot in an indoor (university campus) environment. We compared four different methods: our own approach using existing text detection methods (Minimally Stable Extremal Regions detector and Stroke Width Transform) combined with a convolutional neural network, two modes of the open source program Tesseract, and the experimental mobile app Google Goggles. The results show that a convolutional neural network combined with the Stroke Width Transform gives the best performance in correctly matched text on images with single characters whereas Google Goggles gives the best performance on images with multiple words. The dataset used for this work is released as well.

Source: QUT ePrints (Queensland University of Technology)

Authors: Obadiah Lam, Feras Dayoub, Ruth Schulz, Peter Corke

Institutions: Queensland University of Technology, The University of Queensland

Language: English

Topic: Handwritten Text Recognition Techniques

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: Australian Research Council

Award: Human Cues for Robot Navigation

OpenAlex ID: W2098262060