Research of Text Recognition Based on Natural Scene

Yi Bo Zou; Yi Min Chen

doi:10.4028/www.scientific.net/AMM.599-601.1621

Paper Titles

Recurrence Characteristics Analysis of Near-Surface Wind Speed Signal with Different Sampling Frequencies
p.1605

Research and Simulation of LCMV Algorithm in GNSS Anti-Interference
p.1610

Research of an IPSec VPN Application in Enterprise Network
p.1614

Research of LXI Discovery Method
p.1618

Research of Text Recognition Based on Natural Scene
p.1621

Research of Weapon Training Simulator Software Model Based on UML
p.1625

Research on Combined Weight of Target Threat Index of Information Fusion
p.1629

Research on Flight Altitude Information Fusion Method for ADS/INS/GPS Integrated Systems Based on Federated Filter
p.1636

Research on Information Exchange Platform Based-Web Services for Tourist
p.1640

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 599-601Research of Text Recognition Based on Natural...

Research of Text Recognition Based on Natural Scene

Abstract:

According to the demands of the text recognition in natural scenes, we focus on the text recognition system and its algorithm. Firstly, we present a secondary detection method in which we locate the text area quickly by using the edge of these characters and secondly introduce an improved segmentation algorithm of active contour to detect the location of the target character accurately, based on prior knowledge. Lastly, in the state of text recognition, we propose a KNN (K-Nearest Neighbor) classification method using the descriptor of shape context. The experiments show that our algorithm could achieve better detection rate than others.

You might also be interested in these eBooks

Frontiers of Manufacturing Science and Measuring Technology IV

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 599-601)

Pages:

1621-1624

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.599-601.1621

Citation:

Cite this paper

Online since:

August 2014

Authors:

Yi Bo Zou*, Yi Min Chen

Keywords:

Contour Detection, Shape Context, Text Area Detection, Text Recognition

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] Wang K, Belongie S. Word spotting in the wild[M]. Springer Berlin Heidelberg, (2010).

Google Scholar

[2] Neumann L, Matas J. Real-time scene text localization and recognition[C]/Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on. IEEE, 2012: 3538-3545.

DOI: 10.1109/cvpr.2012.6248097

Google Scholar

[3] Mishra A, Alahari K, Jawahar C V. Top-down and bottom-up cues for scene text recognition[C]/Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on. IEEE, 2012: 2687-2694.

DOI: 10.1109/cvpr.2012.6247990

Google Scholar

[4] Wang T, Wu D J, Coates A, et al. End-to-end text recognition with convolutional neural networks[C]/Pattern Recognition (ICPR), 2012 21st International Conference on. IEEE, 2012: 3304-3308.

Google Scholar

[5] Ezaki N, Bulacu M, Schomaker L. Text detection from natural scene images: towards a system for visually impaired persons[C]/Pattern Recognition, 2004. ICPR 2004. Proceedings of the 17th International Conference on. IEEE, 2004, 2: 683-686.

DOI: 10.1109/icpr.2004.1334351

Google Scholar

[6] Williams D J, Shah M. A fast algorithm for active contours and curvature estimation[J]. CVGIP: Image understanding, 1992, 55(1): 14-26.

DOI: 10.1016/1049-9660(92)90003-l

Google Scholar

[7] Belongie S, Malik J, Puzicha J. Shape matching and object recognition using shape contexts[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 2002, 24(4): 509-522.

DOI: 10.1109/34.993558

Google Scholar