Combining statistical measures to find image text regions
- 11 November 2002
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 450-453 vol.1
- https://doi.org/10.1109/icpr.2000.905373
Abstract
We present a method based on statistical properties of local image pixels for focussing attention on regions of text in arbitrary scenes where the text plane is not necessarily fronto-parallel to the camera. This is particularly useful for desktop or wearable computing applications. The statistical measures are chosen to reveal characteristic properties of text. We combine a number of localised measures using a neural network to classify each pixel as text or non-text. We demonstrate our results on typical images.Keywords
This publication has 3 references indexed in Scilit:
- Location and recovery of text on oriented surfacesPublished by SPIE-Intl Soc Optical Eng ,1999
- Adaptive page segmentation for color technical journals' cover imagesImage and Vision Computing, 1998
- Finding text in imagesPublished by Association for Computing Machinery (ACM) ,1997