A New Kind of Image Edge Detection Based on The Theory of The Adaptive Lifting Wavelet and Morphology

A New Kind of Image Edge Detection Based on The Theory of The Adaptive Lifting Wavelet and Morphology

Honge Ren (College of Information and Computer Engineering, Northeast Forestry University, Forestry Intelligent Equipment Engineering Research Center, Harbin, China), Xiyan Xu (College of Information and Computer Engineering, Northeast Forestry University, Harbin, China), Meng Zhu (College of Information and Computer Engineering, Northeast Forestry University, Forestry Intelligent Equipment Engineering Research Center, Harbin, China) and Dongxu Huo (College of Information and Computer Engineering, Northeast Forestry University, Harbin, China)
Copyright: © 2018 |Pages: 15
DOI: 10.4018/JITR.2018070107

Abstract

This article describes how in traditional edge detection it is prone to defects such as fuzzy positioning, and noise influence. This article proposes a type of edge detection algorithm which combines lifting wavelet transform and adaptive mathematical morphology, which makes a lifting wavelet to analyze the wood cell image. Then, the high-frequency part is detected by using the algorithm fusing the wavelet packet and the rapid-combining multi-scale wavelet, which controls noise effectively; while for the low frequency part is detected with modified adaptive mathematical morphology, to locate the exact details. The final result will processes the edge of the image using “algebra” algorithm fusion. The example for a wood cell image which illustrates the algorithm is to detect the cell boundary relatively clearly, and effectively suppress the noise.
Article Preview

2. Mathematical Morphology For Image Low Frequency Edge Detection

Edge detection method based on mathematical morphology uses structural elements in the form of a certain operator to measure and extract the corresponding shape from image. Through the “on”, “closed” operation can effectively reveal the gray edge of the image, to achieve the aim of image analysis and recognition. Structural elements are actually a gray “form” within a small window, its selection directly have an impact on the effect of image edge extraction.

In general, the window size use , , and window is fastest, the edge extraction is most sophisticated, so this article chooses planar structure elements (Wu, 2015).

Complete Article List

Search this Journal:
Reset
Open Access Articles
Volume 13: 4 Issues (2020): Forthcoming, Available for Pre-Order
Volume 12: 4 Issues (2019): 3 Released, 1 Forthcoming
Volume 11: 4 Issues (2018)
Volume 10: 4 Issues (2017)
Volume 9: 4 Issues (2016)
Volume 8: 4 Issues (2015)
Volume 7: 4 Issues (2014)
Volume 6: 4 Issues (2013)
Volume 5: 4 Issues (2012)
Volume 4: 4 Issues (2011)
Volume 3: 4 Issues (2010)
Volume 2: 4 Issues (2009)
Volume 1: 4 Issues (2008)
View Complete Journal Contents Listing