DocumentCode
671868
Title
Automatic quick-shift method for color image segmentation
Author
Salem, Mahmoud ; Ibrahim, Alif Faisal ; Ali, Hesham A.
Author_Institution
Comput. & Syst. Eng. Dept., Mansoura Univ., Mansoura, Egypt
fYear
2013
fDate
26-28 Nov. 2013
Firstpage
245
Lastpage
251
Abstract
This paper develops a segmentation method using an automatic quick-shift method based on illumination invariant representation of color images. The proposed method segments images into homogeneous regions by applying the quick-shift method with initial parameters, and then automatically gets the final segmented image by changing the quick-shift parameters values. This method is valid for large size images. A quantization process is applied to the invariant image to be used as a reference image. Changing parameters values in iterations instead of using a specific value made the proposed algorithm flexible and robust against different image characteristics. The effectiveness of the proposed method for a variety of images including different objects of metals and dielectrics are examined in experiments by using our color imaging system.
Keywords
gradient methods; image colour analysis; image representation; image segmentation; automatic quick-shift method; color image segmentation; dielectrics; homogeneous regions; illumination invariant representation; metals; quick-shift parameters values; reference image; Frequency modulation; IP networks; Iron; Quick-shift; color image segmentation; quantization; superpixel invariant feature;
fLanguage
English
Publisher
ieee
Conference_Titel
Computer Engineering & Systems (ICCES), 2013 8th International Conference on
Conference_Location
Cairo
Print_ISBN
978-1-4799-0078-7
Type
conf
DOI
10.1109/ICCES.2013.6707212
Filename
6707212
Link To Document