[go: up one dir, main page]
More Web Proxy on the site http://driver.im/ skip to main content
article

A novel adaptive morphological approach for degraded character image segmentation

Published: 01 November 2005 Publication History

Abstract

This work proposes a novel adaptive approach for character segmentation and feature vector extraction from seriously degraded images. An algorithm based on the histogram automatically detects fragments and merges these fragments before segmenting the fragmented characters. A morphological thickening algorithm automatically locates reference lines for separating the overlapped characters. A morphological thinning algorithm and the segmentation cost calculation automatically determine the baseline for segmenting the connected characters. Basically, our approach can detect fragmented, overlapped, or connected character and adaptively apply for one of three algorithms without manual fine-tuning. Seriously degraded images as license plate images taken from real world are used in the experiments to evaluate the robustness, the flexibility and the effectiveness of our approach. The system approach output data as feature vectors keep useful information more accurately to be used as input data in an automatic pattern recognition system.

References

[1]
Taxt, T., Flynn, P.J. and Jain, A.K., Segmentation of document images. IEEE Trans. Pattern Anal. Machine Intell. v11 i12. 1322-1329.
[2]
Lu, Y., Machine printed character segmentation-an overview. Pattern Recognition. v28 i1. 67-80.
[3]
Tan, C.L., Huang, W., Yu, Z. and Xu, Y., Image document text retrieval without OCR. IEEE Trans. Pattern Anal. Machine Intell. v24 i6. 838-844.
[4]
M.C. Jung, Y.C. Shin, S.N. Srihari, Machine printed character segmentation method using side profiles, IEEE SMC '99 Conference Proceedings, vol. 6, No. 10, 1999, pp. 863-867.
[5]
N. Arica, F. Yarman-Vural, A new scheme for off-line handwritten connected digit recognition, Proceedings of the International Conference on Pattern Recognition, vol. 1, 1998, pp. 127-129.
[6]
Lee, S. and Kim, S., Integrated segmentation and recognition of handwritten numerals with cascade neural network. IEEE Trans. Systems Man Cybern. v29 i2. 285-290.
[7]
S. Nomura, K. Yamanaka, O. Katai, New adaptive methods applied to printed word image binarization, Proceedings of the Fourth IASTED International Conference Signal and Image Processing, August 12-14, 2002, pp. 288-293.
[8]
S. Nomura, New methods for image binarization and character segmentation applied to an automatic recognition system of number plates, M.S. Thesis, Faculty of Electrical Engineering, Federal University of Uberlíndia, Uberlíndia City, Brazil, 2002 (in Portuguese).
[9]
Gao, H., Siu, W. and Hou, C., Improved techniques for automatic image segmentation. IEEE Trans. Circuits Systems Video Technol. v11 i12. 1273-1280.
[10]
Serra, J., . 1982. Image Analysis and Mathematical Morphology, 1982.Academic Press, London.
[11]
Serra, J., . 1988. Image Analysis and Mathematical Morphology, Theoretical Advances, 1988.Academic Press, London.
[12]
Gonzalez, R.C. and Woods, R.E., Digital Image Processing. 1993. Addison-Wesley Publishing Company, Reading, MA.
[13]
Park, H.S. and Ra, J.B., Efficient image segmentation preserving semantic object shapes. IEICE Trans. Fund. vE82-A i6. 879-886.
[14]
Salembier, P. and Pardas, M., Hierarchical morphological segmentation for image sequence coding. IEEE Trans. Image Process. v3 i5. 639-651.
[15]
Kimura, F., Tsuruoka, S., Miyake, Y. and Shridhar, M., A lexicon directed algorithm for recognition of unconstrained handwritten words. IEICE Trans. Inform. Systems. vE77-D i7. 785-793.
[16]
Elnagar, A. and Alhajj, R., Segmentation of connected handwritten numeral strings. Pattern Recognition. v36. 625-634.
[17]
Jang, B. and Chin, R., One-pass parallel thinning: analysis, properties, and quantitative evaluation. IEEE PAMI. v14 i11. 1129-1140.
[18]
Soille, P., Morphological Image Analysis: Principles and Applications. 1999. Springer, Berlin.
[19]
Nomura, S., Yamanaka, K., Katai, O. and Kawakami, H., A new method for degraded color image binarization based on adaptive lightning on grayscale versions. IEICE Trans. Inform. Systems E. v87-D i4. 1012-1020.
[20]
L.S. Oliveira, E. Lethelier, F. Bortolozzi, R. Sabourin, A new approach to segment handwritten digits, Proceedings of the Seventh International Workshop on Frontiers in Handwriting Recognition, 2000, pp. 577-582.

Cited By

View all
  • (2022)License plate recognition system based on the difference of convolutional neural network framework2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC)10.1109/ITSC55140.2022.9922058(799-804)Online publication date: 8-Oct-2022
  • (2021)Performance enhancement method for multiple license plate recognition in challenging environmentsJournal on Image and Video Processing10.1186/s13640-021-00572-42021:1Online publication date: 17-Sep-2021
  • (2021)Recognition System for Libyan Vehicle License PlateThe 7th International Conference on Engineering & MIS 202110.1145/3492547.3492595(1-6)Online publication date: 11-Oct-2021
  • Show More Cited By
  1. A novel adaptive morphological approach for degraded character image segmentation

      Recommendations

      Comments

      Please enable JavaScript to view thecomments powered by Disqus.

      Information & Contributors

      Information

      Published In

      cover image Pattern Recognition
      Pattern Recognition  Volume 38, Issue 11
      November, 2005
      434 pages

      Publisher

      Elsevier Science Inc.

      United States

      Publication History

      Published: 01 November 2005

      Author Tags

      1. Adaptive segmentation
      2. Connected characters
      3. Degraded images
      4. Feature extraction
      5. Fragmented characters
      6. Mathematical morphology
      7. Overlapped characters
      8. Pattern recognition

      Qualifiers

      • Article

      Contributors

      Other Metrics

      Bibliometrics & Citations

      Bibliometrics

      Article Metrics

      • Downloads (Last 12 months)0
      • Downloads (Last 6 weeks)0
      Reflects downloads up to 21 Dec 2024

      Other Metrics

      Citations

      Cited By

      View all
      • (2022)License plate recognition system based on the difference of convolutional neural network framework2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC)10.1109/ITSC55140.2022.9922058(799-804)Online publication date: 8-Oct-2022
      • (2021)Performance enhancement method for multiple license plate recognition in challenging environmentsJournal on Image and Video Processing10.1186/s13640-021-00572-42021:1Online publication date: 17-Sep-2021
      • (2021)Recognition System for Libyan Vehicle License PlateThe 7th International Conference on Engineering & MIS 202110.1145/3492547.3492595(1-6)Online publication date: 11-Oct-2021
      • (2021)Air-TextProceedings of the 29th ACM International Conference on Multimedia10.1145/3474085.3475694(1267-1274)Online publication date: 17-Oct-2021
      • (2021)Text Recognition in the WildACM Computing Surveys10.1145/344075654:2(1-35)Online publication date: 5-Mar-2021
      • (2021)Scene Text Detection and Recognition: The Deep Learning EraInternational Journal of Computer Vision10.1007/s11263-020-01369-0129:1(161-184)Online publication date: 1-Jan-2021
      • (2018)Characters Recognition of Binary Image using KNNProceedings of the 4th International Conference on Virtual Reality10.1145/3198910.3234651(116-118)Online publication date: 24-Feb-2018
      • (2018)Geometric Alignment by Deep Learning for Recognition of Challenging License Plates2018 21st International Conference on Intelligent Transportation Systems (ITSC)10.1109/ITSC.2018.8569259(3524-3529)Online publication date: 4-Nov-2018
      • (2017)Hierarchical and Networked Vehicle Surveillance in ITSIEEE Transactions on Intelligent Transportation Systems10.1109/TITS.2016.255277818:1(25-48)Online publication date: 1-Jan-2017
      • (2017)Efficient character segmentation approach for machine-typed documentsExpert Systems with Applications: An International Journal10.1016/j.eswa.2017.03.02780:C(210-231)Online publication date: 1-Sep-2017
      • Show More Cited By

      View Options

      View options

      Media

      Figures

      Other

      Tables

      Share

      Share

      Share this Publication link

      Share on social media