A Real-Time Scene Text to Speech System
An end-to-end real-time scene text localization and recognition method is demonstrated. The method localizes textual content in images, a video or a webcam stream, performs character recognition (OCR) and “reads” it out loud using a text-to-speech engine. The method has been recently published, achieves state-of-the-art results on public datasets and is able to recognize different fonts and scripts including non-latin ones.
The real-time performance is achieved by posing the character detection problem as an efficient sequential selection from the set of Extremal Regions (ERs) which has a linear computation complexity in the number of pixels in the image. Robustness to blur, noise and illumination and color variations is also demonstrated. Finally, we show effects of various control parameters.
- 1.Jung-Jin, L., Lee, P.H., Lee, S.W., Yuille, A., Koch, C.: Adaboost for text detection in natural scene. In: ICDAR 2011, pp. 429–434 (2011)Google Scholar
- 2.Chen, X., Yuille, A.L.: Detecting and reading text in natural scenes. In: CVPR, vol. 2, pp. 366–373 (2004)Google Scholar
- 4.Pan, Y.F., Hou, X., Liu, C.L.: Text localization in natural scene images based on conditional random field. In: ICDAR 2009, pp. 6–10. IEEE Computer Society (2009)Google Scholar
- 5.Epshtein, B., Ofek, E., Wexler, Y.: Detecting text in natural scenes with stroke width transform. In: CVPR 2010, pp. 2963–2970 (2010)Google Scholar
- 7.Neumann, L., Matas, J.: Real-time scene text localization and recognition. In: CVPR 2012 (to appear, 2012)Google Scholar
- 8.Neumann, L., Matas, J.: Text localization in real-world images using efficiently pruned exhaustive search. In: ICDAR 2011, pp. 687–691 (2011)Google Scholar