Character Detection and String Identification on a Signboard in Scene Image Based on Criterions of Segmented Images

Abstract:

In this paper, a method which specifies the signboard region and extracts the charactersinside the signboard is proposed.We usually take notes not to forget what we should leave to memory.But it is often that the task is too troublesome. Our aim is the development of a new input-interface soas to input texts froma picture.Most of signboards are composed of almostmonochromatic region. Onthe basis of this observation, image segmentation using color information is applied, and then we getsome binary images by applying threshold for each segmented region. Each binary image is enclosedby the smallest circumscribed square. The signboard region is specified according to distribution andarea of the white pixels inside the square. As a result of experiment, we confirmed the effectivenessof the proposed method.

• Periodical: Applied Mechanics and Materials (Volume 103)
• Pages: 658-666
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.103.658
• Online since: September 2011
• Authors: Hideaki Kawano, Hideaki Orii, Hiroshi Maeda
• Keywords: Character Detection, Clustering, Image Segmentation, Scene Image, Signboard

References

[1] K. Negishi, M. Iwamura, S. Omachi, H. Aso, Isolated character recognition by searching features in scene images, in: Proc. First International Workshop on Camera-Based Document Analysis and Recognition, CBDAR2005, 2005, pp.140-147.

DOI: 10.1109/icdar.2005.147

[2] K. Hirayama, S. Omachi, H. Aso, String extraction from scene images using color and luminance information (in japanese), IEICE Transactions on Information and Systems (Japanese Edition) J89-D2 (4) (2006) 893-896.

[3] K. Ashida, H. Nagai, M. Okamoto, H. Miyano, H. Yamamoto, Extraction of characters from scene images (in japanese), IEICE Transactions on Information and Systems (Japanese Edition) J88-D2 (9) (2005) 1817-1824.

[4] K. Matsuo, K. Ueda, M. Umeda, Extraction of character string region on signboard from scene image using adaptive threshold methods (in japanese), IEICE Transactions on Information and Systems (Japanese Edition) J80-D2 (6) (1997) 1617-16o26.

[5] N. Otsu, An automatic threshold selection method based on descriminant and least squares criterior (in japanese), IECE Transactions on Information and Systems (Japanese Edition) J63-D (4) (1980) 349-356.

[6] J. A. K. Wang, Character location in scene images from digital camera, in: Pattern Recognition, 2003, pp.2287-2299.

DOI: 10.1016/s0031-3203(03)00082-7