Robust text detection in natural images with edge-enhanced Maximally Stable Extremal Regions

• Published in: 2011 18th IEEE International Conference on Image Processing pp. 2609 - 2612
• Main Authors: Chen, H., Tsai, S. S., Schroth, G., Chen, D. M., Grzeszczuk, R., Girod, B.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.09.2011
• Subjects: Conferences; connected component analysis; Detection algorithms; Feature extraction; Image edge detection; maximally stable extremal regions; Robustness; Text detection; Transforms; Visualization

Detecting text in natural images is an important prerequisite. In this paper, we propose a novel text detection algorithm, which employs edge-enhanced Maximally Stable Extremal Regions as basic letter candidates. These candidates are then filtered using geometric and stroke width information to excl...