Abstract
On the basis of traditional gray level co-occurrence matrix (GLCM) and 8-neighborhood element matrix, a novel 20- or twenty-neighborhood color motif co-occurrence matrix (TCMCM) is proposed and used to extract the foreground in color videos. The processing of extracting the foreground is briefly described as follows. First, the background is constructed by averaging the first many frames of the considered video. Following this, the TCMCM of each point is computed in the current frame and background frame respectively. Next, based on the TCMCM, the entropy, moment of inertia and energy in each of their color channel are introduced to represent color texture features. Finally, Euclidean distance is used to measure the similarity of color texture features between the foreground and background. Experimental results show that the presented method can be effectively applied to foreground extraction in color video, and can get better performance on the foreground extraction than the traditional method based on GLCM.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Lin, G., Wang, C.: Improved three frame difference method and background difference method a combination of moving target detection algorithm. Equip. Manuf. Technol. 3, 172–173 (2018)
Fu, D.: Vehicle detection algorithm based on background modeling. University of Science and Technology of China, Hefei (2015)
Guo, C.: Target tracking algorithm based on improved five-frame difference and mean shift. J. Langfang Normal Univ. 18(1), 21–24 (2018)
Jian, C., Hu, J., Cui, G.: Texture feature extraction method of camouflage effect evaluation model. Comm. Control Simul. 39(3), 102–105 (2017)
Gao, C., Hui, X.: GLCM-Based texture feature extraction. Comput. Syst. Appl. 19(6), 195–198 (2010)
Liu, X.: ROI digital watermarking based on texture characteristics. Hangzhou Dianzi University, Hangzhou (2011)
Wang, L., Ou, Z.: Image texture analysis by grey-primitive co-occurrence matrix. Comput. Eng. 30(23), 19–21 (2004)
Hou, J., Chen, Y., He, S., et al.: New definition of image texture feature. Comput. Appl. Softw. 24(9), 157–158 (2007)
Song, L., Wang, X.: An image retrieval algorithm integrating color and texture features. Comp. Eng. Appl. 47(34), 203–206 (2011)
Yu, S., Zeng, J., Xie, L.: Image retrieval algorithm based on multi-feature fusion. Comput. Eng. 38(24), 216–219 (2012)
Haralick, R.M., Shanmugam, K., Dinstein, I.: Textural features for image classification. IEEE Trans. Syst. Man Cybern. 3(6), 610–621 (1973)
Ghulam, M., Mohammed, A., Hossain, M., et al.: Enhanced living by assessing voice pathology using a co-occurrence matrix. Sensors 17(2), 267 (2017)
Wang, H., Li, H.: Classification recognition of impurities in seed cotton based on local binary pattern and gray level co-occurrence matrix. Trans. Chin. Soc. Agric. Eng. 31(3), 236–240 (2015)
Wang, L., Ou, Z., Su, T., et al.: Content-based image retrieval in database using SVM and gray primitive co-occurrence matrix. J. Dalian Univ. Technol. (4), 475–478 (2003)
Xu, F.: Classification of texture features based on color symbiosis matrix. J. Zhejiang Ind. Trade Vocat. Coll. 16(4), 54–58 (2016)
Gui, W., Liu, J., Yang, C., et al.: Color co-occurrence matrix based froth image texture extraction for mineral flotation. Miner. Eng. 60–67 (2013)
Jiao, P., Guo, Y., Liu, L., et al.: Implementation of gray level co-occurrence matrix texture feature extraction using Matlab. Comput. Technol. Dev. 22(11), 169–171 (2012)
Acknowledgements
This work is supported by Educational Research Project for Young and Middle-aged Teachers of Fujian No. JAT-170667 and Teaching Reform Project of Fuqing Branch of Fujian Normal University No. XJ14010.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Guo, CF., Chen, G.T., Xu, L., Xie, CF. (2020). Foreground Extraction Based on 20-Neighborhood Color Motif Co-occurrence Matrix. In: Pan, JS., Li, J., Tsai, PW., Jain, L. (eds) Advances in Intelligent Information Hiding and Multimedia Signal Processing. Smart Innovation, Systems and Technologies, vol 157. Springer, Singapore. https://doi.org/10.1007/978-981-13-9710-3_29
Download citation
DOI: https://doi.org/10.1007/978-981-13-9710-3_29
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-13-9709-7
Online ISBN: 978-981-13-9710-3
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)