Wuand, Y. and Shivakumara, P. and Tong Lu and Tan, Chew Lim and Blumenstein, Michael and Hemantha Kumar, G. (2016) Contour restoration of text components for recognition in video/scene images. IEEE Transactions on Image Processing, 25 (12). pp. 5622-5634.
Full text not available from this repository. (Request a copy)Abstract
Text recognition in video/natural scene images has gained significant attention in the field of image processing in many computer vision applications, which is much more challenging than recognition in plain background images. In this paper, we aim to restore complete character contours in video/scene images from gray values, in contrast to the conventional techniques that consider edge images/binary information as inputs for text detection and recognition. We explore and utilize the strengths of zero crossing points given by the Laplacian to identify stroke candidate pixels (SPC). For each SPC pair, we propose new symmetry features based on gradient magnitude and Fourier phase angles to identify probable stroke candidate pairs (PSCP). The same symmetry properties are proposed at the PSCP level to choose seed stroke candidate pairs (SSCP). Finally, an iterative algorithm is proposed for SSCP to restore complete character contours. Experimental results on benchmark databases, namely, the ICDAR family of video and natural scenes, Street View Data, and MSRA data sets, show that the proposed technique outperforms the existing techniques in terms of both quality measures and recognition rate. We also show that character contour restoration is effective for text detection in video and natural scene images.
| Item Type: | Article |
|---|---|
| Uncontrolled Keywords: | computer vision;Fourier transforms;image recognition;image restoration;iterative methods;text detection;MSRA data sets;street view data;ICDAR family;benchmark database;iterative algorithm;seed stroke candidate pairs;probable stroke candidate pairs;Fourier phase angles;gradient magnitude;symmetry features;stroke candidate pixels;zero crossing points;text detection;binary information;edge images;gray values;plain background images;computer vision;natural scene images;video scene images;text recognition;image recognition;text components;complete character contour restoration;Text recognition;Character recognition;Shape;Image edge detection;Image restoration;Feature extraction;Laplacian;zero crossing points;gradient magnitude;Fourier phase angle;character reconstruction;video text recognition;object recognition |
| Subjects: | D Physical Science > Computer Science |
| Divisions: | Department of > Computer Science |
| Depositing User: | Manjula P Library Assistant |
| Date Deposited: | 18 Jun 2019 07:23 |
| Last Modified: | 18 Jun 2019 07:23 |
| URI: | http://eprints.uni-mysore.ac.in/id/eprint/3309 |
Actions (login required)
 |
View Item |
