Abstract
A mixed scheme based on Wavelet Transformation (WT) is proposed for image edge detection. The scheme combines the wavelet transform and traditional Sobel and LoG (Laplacian of Gaussian) operator edge-detection algorithms. The precise theory analysis is given to show that the wavelet transformation has an advantage for signal processing. Simulation results show that the new scheme is better than only using the Sobel or LoG methods. Complexity analysis is also given and the conclusion is acceptable, therefore the proposed scheme is effective for edge detection.
Similar content being viewed by others
References
Bruce N. Nelson, Paul Slebodnick, Edward J. Lemieux, et al., Wavelet processing for image de-noising and edge detection algorithm used in shipboard ballast tank video inspection system, in Wavelet Application VIII, Harold H. Szu, Proceedings of SPIE 2001, Vol.4391, 134–145.
Zhang Xianda, Bao Zheng, Analysis and Processing of Non-Stationary Signals, Beijing, Defense Industry Publishing House, 1998, Chapter 7–8 (in Chinese).
Peng Jinye, Yu Bianzhang, Wang Daikai, Images similarity detection based on directional gradient angular histogram, IEEE Proceeding on ICPR’ 2002, 8, Quebec, Canada, Vol.1, 147–50.
S. Mallat, A theory for multiresolution: The wavelet representation, IEEE Trans. on Pattern Analysis and Machine Intelligence, 11(1989)7, 674–693.
Chen Fengshi, et al., Principle and Application of Wavelet Transformation in Signal-Processing, Beijing, Defense Industry Publishing House, 1997, Chapter 1–2 (in Chinese).
Author information
Authors and Affiliations
Additional information
Supported by the National Defence 973 project (2002HS0604, 2002HS0634)
About this article
Cite this article
Xie, H., Yu, B. & Zhao, J. Mixed scheme for image edge detection based on Wavelet Transform. J. of Electron.(China) 21, 471–475 (2004). https://doi.org/10.1007/BF03036998
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF03036998