Detecting and reading text in natural scenes

This paper gives an algorithm for detecting and reading text in natural images. The algorithm is intended for use by blind and visually impaired subjects walking through city scenes. We first obtain a dataset of city images taken by blind and normally sighted subjects. From this dataset, we manually label and extract the text regions. Next we perform statistical analysis of the text regions to determine which image features are reliable indicators of text and have low entropy (i.e. feature response is similar for all text images). We obtain weak classifiers by using joint probabilities for feature responses on and off text. These weak classifiers are used as input to an AdaBoost machine learning algorithm to train a strong classifier. In practice, we trained a cascade with 4 strong classifiers containing 79 features. An adaptive binarization and extension algorithm is applied to those regions selected by the cascade classifier. Commercial OCR software is used to read the text or reject it as a non-text region. The overall algorithm has a success rate of over 90% (evaluated by complete detection and reading of the text) on the test set and the unread text is typically small and distant from the viewer.