Combining Statistical Measures to Find Image Text Regions

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 charactersitic 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.

• Type: Conference
• Year: 2000
• Where: ICPR
• Authors: Paul Clark, Majid Mirmehdi
• Keywords: Computer Vision, ICPR 2000, Local Image Pixels, Text Plane, Wearable Computing Applications