Dissertation
Dissertation > Industrial Technology > Automation technology,computer technology > Computing technology,computer technology > Computer applications > Information processing (information processing) > Pattern Recognition and devices > Image recognition device

Research on Application of Impulse Detection and Morphology in Image Filter and Edge Detection

Author ChenHengJin
Tutor MaXiaoHu
School Suzhou University
Course Applied Computer Technology
Keywords impulse detection image filter mathematics morphology edge detection
CLC TP391.41
Type Master's thesis
Year 2009
Downloads 110
Quotes 1
Download Dissertation

Image engineering can be arranged into three catalogs according to class in term of research approach,namely image engineering is combination of image processing,image analysis and image understanding and their engineering application.Image filter and edge detection are the foundation of image processing.Image filter and edge detection are also hot topic in digital image processing.The technology of impulse detection is the key technology of image filter of impulse noise.Mathematics morphology is based on set theory,which is a powerful approach in geometrical description and nonlinear filtering.This paper discusses image filter algorithm of impulse noise and application of morphology in image filter and edge detection.Major contributions list as follows:1.A new filtering noise algorithm based on improved impulse noise detection is proposed.Firstly,the algorithm marks noise points in the noise marking matrix by improved noise detection method;Then,the impulse noise in gray image is filtered efficiently by using improved median filtering with adaptive adjustment filtering window. On this basis,in each color channel of an image based on the RGB color space,the noise is filtered separately using the new method;Finally,it can get the final color filtered image by the channel fusion technology.2.An adaptive generalized morphological filter is proposed.The filter can solve difficulty of structural elements selection and overcome the bias filtering output problem of the traditional filter.Based on this,an edge detection algorithm based on multi-structural elements and multi-scale morphology is proposed.The algorithm is acquired by improving edge detection operator and designing adaptive edge synthesis formula.And then,the method is used successfully to filter and detect edge information of Jiaguwen and inscription images.3.To solve selection problem of the scale of structural elements,an adaptive algorithm to define optional size of structure element is proposed based on order morphology.4.Mathematical morphology is extended to soft morphology,and extended to color images.In the HSV color space,a new vector sorting method is defined.Based on new vector sorting method,a new color image processing method was proposed based on soft multi-structural elements.

Related Dissertations
More Dissertations