A Novel Segmentation Algorithm for Complex Images Based on Valid Gradient

Article Preview

Abstract:

Traditional image segmentation algorithms usually can’t obtain expected effects when facing with complex images such as container code images with complex backgrounds and bad illuminations. This paper introduces the definition of valid gradient and proposes a novel image segmentation algorithm based on it to solve above problem. Through statistical analyzing of the valid gradient information of the edges between the target and the background, some thresholds can be obtained directly and used to segment the images. The experiment results show that the algorithm can get better performance evaluation. Finally, the algorithm has good practicability and can be used directly in different image segmentation fields.

You might also be interested in these eBooks

Info:

Periodical:

Pages:

3954-3958

Citation:

Online since:

December 2010

Authors:

Export:

Price:

Permissions CCC:

Permissions PLS:

Сopyright:

© 2011 Trans Tech Publications Ltd. All Rights Reserved

Share:

Citation:

[1] Zhang Yujin, Image segmentation, Beijing: Science Press (2001).

Google Scholar

[2] Ismael Salvador Igual, Gabriela Andreu Garcia, Alberto Perez Jimenez, Preprocessing and recognition of characters in container codes. Proceedings of IEEE 16th International Conference on Pattern Recognition, 3(2002) 143-146.

DOI: 10.1109/icpr.2002.1047815

Google Scholar

[3] He Zhiwei, Liu Jilin, et al., A new automatic extraction method of container identity codes, Proceedings of IEEE Intelligent Transportation Systems, 6 (2005) 72-78.

DOI: 10.1109/itsc.2003.1252771

Google Scholar

[4] M. Goccia, M. Bruzzo, et al., Recognition of container code characters through gray-level feature extraction and gradient-based classifier optimization, Proceedings of IEEE 7th International Conference on Document Analysis and Recognition, (2003).

DOI: 10.1109/icdar.2003.1227804

Google Scholar

[5] Wang Jia-nan, Kong Jun, A region-based SRG algorithm for color image segmentation, Proceedings of the IEEE 6th International Conference on Machine Learning and Cybernetics, (2007) 15422-15471.

DOI: 10.1109/icmlc.2007.4370390

Google Scholar

[6] Zhang Jian-wei, Ge Qi, MR image segmentation of fast CV model based on local statistic information, Journal of Image and Graphics, 15(1) (2010) 69-74.

Google Scholar

[7] J.R. Parker, Gray level thresholding in badly illuminated images, IEEE Trans. on Pattern Analysis and Machine Intelligence, 13(8) (1991) 813-819.

DOI: 10.1109/34.85672

Google Scholar