Skip to main content
Erschienen in:
Buchtitelbild

2015 | OriginalPaper | Buchkapitel

Fast and Accurate Text Detection in Natural Scene Images

verfasst von : Chengqiu Xiao, Lixin Ji, Chao Gao, Shaomei Li

Erschienen in: Intelligence Science and Big Data Engineering. Image and Video Data Engineering

Verlag: Springer International Publishing

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

Repeating component filtering is problematic for the accuracy and speed of scene text detection. This paper proposes a fast and accurate method for detecting scene text. A novel MSER tree pruning algorithm is proposed to extract unique Maximally Stable Extremal Regions (MSERs) as character candidates. Two cues specially designed for capturing the intrinsic features of characters are integrated by a Bayesian classifier. Character candidates are grouped into text candidates by some characteristics between words and then they are verified with some efficient rules in a crossing line. Experimental results on the ICDAR 2011 Robust Reading Competition dataset demonstrate that the performance of our much simpler method is slightly lower than the state-of-the-art performance, however, the processing speed of this algorithm is at least four times faster.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literatur
1.
Zurück zum Zitat Lee, J.-J., Lee, P.-H., Lee, S.-W., Yuille, A.L., Koch, C.: Adaboost for text detection in natural scene. In: Proceedings of the IEEE International Conference on Document Analysis and Recognition, pp. 429–434 (2011) Lee, J.-J., Lee, P.-H., Lee, S.-W., Yuille, A.L., Koch, C.: Adaboost for text detection in natural scene. In: Proceedings of the IEEE International Conference on Document Analysis and Recognition, pp. 429–434 (2011)
2.
Zurück zum Zitat Chen, X., Yuille, A.L.: Detecting and reading text in natural scenes. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 366–373 (2004) Chen, X., Yuille, A.L.: Detecting and reading text in natural scenes. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 366–373 (2004)
3.
Zurück zum Zitat Epshtein, B., Ofek, E., Wexler, Y.: Detecting text in natural scenes with stroke width transform. In: CVPR, pp. 2963–2970 (2010) Epshtein, B., Ofek, E., Wexler, Y.: Detecting text in natural scenes with stroke width transform. In: CVPR, pp. 2963–2970 (2010)
4.
Zurück zum Zitat Li, Y., Shen, C., Jia, W., van den Hengel, A.: Leveraging surrounding context for scene text detection. In: Proceedings of IEEE International Conference on Image Processing, pp. 2264–2268 (2013) Li, Y., Shen, C., Jia, W., van den Hengel, A.: Leveraging surrounding context for scene text detection. In: Proceedings of IEEE International Conference on Image Processing, pp. 2264–2268 (2013)
5.
Zurück zum Zitat Li, Y., Lu, H.: Scene text detection via stroke width. In: Proceedings of IEEE International Conference on Pattern Recognition, pp. 681–684 (2012) Li, Y., Lu, H.: Scene text detection via stroke width. In: Proceedings of IEEE International Conference on Pattern Recognition, pp. 681–684 (2012)
6.
Zurück zum Zitat Pan, Y.-F., Hou, X., Liu, C.-L.: A hybrid approach to detect and localize texts in natural scene images. IEEE Trans. Image Process. 20, 800–813 (2011)MathSciNetCrossRef Pan, Y.-F., Hou, X., Liu, C.-L.: A hybrid approach to detect and localize texts in natural scene images. IEEE Trans. Image Process. 20, 800–813 (2011)MathSciNetCrossRef
7.
Zurück zum Zitat Neumann, L., Matas, J.: A method for text localization and recognition in real-world images. In: Kimmel, R., Klette, R., Sugimoto, A. (eds.) ACCV 2010, Part III. LNCS, vol. 6494, pp. 770–783. Springer, Heidelberg (2011) CrossRef Neumann, L., Matas, J.: A method for text localization and recognition in real-world images. In: Kimmel, R., Klette, R., Sugimoto, A. (eds.) ACCV 2010, Part III. LNCS, vol. 6494, pp. 770–783. Springer, Heidelberg (2011) CrossRef
8.
Zurück zum Zitat Neumann, L., Matas, J.: Real-time scene text localization and recognition. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3538–3545 (2012) Neumann, L., Matas, J.: Real-time scene text localization and recognition. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3538–3545 (2012)
9.
Zurück zum Zitat Matas, J.G., Zimmermann, K.: A new class of learnable detectors for categorisation. In: Kalviainen, H., Parkkinen, J., Kaarna, A. (eds.) SCIA 2005. LNCS, vol. 3540, pp. 541–550. Springer, Heidelberg (2005) CrossRef Matas, J.G., Zimmermann, K.: A new class of learnable detectors for categorisation. In: Kalviainen, H., Parkkinen, J., Kaarna, A. (eds.) SCIA 2005. LNCS, vol. 3540, pp. 541–550. Springer, Heidelberg (2005) CrossRef
10.
Zurück zum Zitat Chen, H., Tsai, S., Schroth, G., Chen, D., Grzeszczuk, R., Girod, B.: Robust text detection in natural images with edge-enhanced maximally stable extremal regions. In: Proceedings of IEEE International Conference on Image Processing, pp. 2609–2612 (2011) Chen, H., Tsai, S., Schroth, G., Chen, D., Grzeszczuk, R., Girod, B.: Robust text detection in natural images with edge-enhanced maximally stable extremal regions. In: Proceedings of IEEE International Conference on Image Processing, pp. 2609–2612 (2011)
11.
Zurück zum Zitat Neumann, L., Matas, J.: Text localization in real-world images using efficiently pruned exhaustive search. In: ICDAR, pp. 687–691 (2011) Neumann, L., Matas, J.: Text localization in real-world images using efficiently pruned exhaustive search. In: ICDAR, pp. 687–691 (2011)
12.
Zurück zum Zitat Yin, X.C., Yin, X.W., Huang, K.: Robust text detection in natural scene images. IEEE Trans. Pattern Anal. Mach. Intell. 36, 970–983 (2014)CrossRef Yin, X.C., Yin, X.W., Huang, K.: Robust text detection in natural scene images. IEEE Trans. Pattern Anal. Mach. Intell. 36, 970–983 (2014)CrossRef
13.
Zurück zum Zitat Zhang, J., Kasturi, R.: Text detection using edge gradient and graph spectrum. In: Proceedings of IEEE International Conference on Pattern Recognition, pp. 3979–3982 (2010) Zhang, J., Kasturi, R.: Text detection using edge gradient and graph spectrum. In: Proceedings of IEEE International Conference on Pattern Recognition, pp. 3979–3982 (2010)
14.
Zurück zum Zitat Li, Y., Jia, W., Shen, C., van den Hengel, A.: Characterness: an indicator of text in the wild. In: Proceedings of IEEE International Conference on Image Processing, pp. 1666–1677 (2014) Li, Y., Jia, W., Shen, C., van den Hengel, A.: Characterness: an indicator of text in the wild. In: Proceedings of IEEE International Conference on Image Processing, pp. 1666–1677 (2014)
15.
Zurück zum Zitat Huang, W., Qiao, Y., Tang, X.: Robust scene text detection with convolution neural network induced MSER trees. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part IV. LNCS, vol. 8692, pp. 497–511. Springer, Heidelberg (2014) Huang, W., Qiao, Y., Tang, X.: Robust scene text detection with convolution neural network induced MSER trees. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part IV. LNCS, vol. 8692, pp. 497–511. Springer, Heidelberg (2014)
16.
Zurück zum Zitat Shi, C., Wang, C., Xiao, B., Zhang, Y., Gao, S.: Scene text detection using graph model built upon maximally stable extremal regions. Pattern Recogn. Lett. 34, 107–116 (2013)CrossRef Shi, C., Wang, C., Xiao, B., Zhang, Y., Gao, S.: Scene text detection using graph model built upon maximally stable extremal regions. Pattern Recogn. Lett. 34, 107–116 (2013)CrossRef
17.
Zurück zum Zitat Yi, C., Tian, Y.: Text extraction from scene images by character appearance and structure modeling. CVIU 117(2), 182–194 (2013) Yi, C., Tian, Y.: Text extraction from scene images by character appearance and structure modeling. CVIU 117(2), 182–194 (2013)
18.
Zurück zum Zitat Shahab, A., Shafait, F., Dengel, A.: ICDAR 2011 robust reading competition challenge 2: reading text in scene images. In: Proceedings of International Conference on Document Analysis and Recognition, pp. 1491–1496 (2011) Shahab, A., Shafait, F., Dengel, A.: ICDAR 2011 robust reading competition challenge 2: reading text in scene images. In: Proceedings of International Conference on Document Analysis and Recognition, pp. 1491–1496 (2011)
Metadaten
Titel
Fast and Accurate Text Detection in Natural Scene Images
verfasst von
Chengqiu Xiao
Lixin Ji
Chao Gao
Shaomei Li
Copyright-Jahr
2015
DOI
https://doi.org/10.1007/978-3-319-23989-7_1

Premium Partner