Self-Quotient ε-Filter for Feature Extraction from Noise Corrupted Image

Mitsuharu MATSUMOTO  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E93-D   No.11   pp.3066-3075
Publication Date: 2010/11/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.E93.D.3066
Print ISSN: 0916-8532
Type of Manuscript: PAPER
Category: Image Recognition, Computer Vision
Keyword: 
feature extraction,  nonlinear filter,  self-quotient ε-filter,  Gaussian noise,  impulse noise,  

Full Text: PDF(4MB)>>
Buy this Article




Summary: 
This paper describes a nonlinear filter that can extract the image feature from noise corrupted image labeled self-quotient ε-filter (SQEF). SQEF is an improved self-quotient filter (SQF) to extract the image feature from noise corrupted image. Although SQF is a simple approach for feature extraction from the images, it is difficult to extract the feature when the image includes noise. On the other hand, SQEF can extract the image feature not only from clear images but also from noise corrupted images with uniform noise, Gaussian noise and impulse noise. We show the algorithm of SQEF and describe its feature when it is applied to uniform noise corrupted image, Gaussian noise corrupted image and impulse noise corrupted image. Experimental results are also shown to confirm the effectiveness of the proposed method.