DocumentCode
2817244
Title
A method to determine the size of the structuring element in morphological correction of non-uniform illumination
Author
Lorenzo-Ginori, Juan V.
Author_Institution
Fac. of Electr. Eng., Univ. Central “Marta Abreu” de Las Villas, Las Villas, Cuba
fYear
2011
fDate
11-14 Sept. 2011
Firstpage
1453
Lastpage
1456
Abstract
Correction of uneven illumination in images is frequently used as a preprocessing step, for which morphological processing is a well established technique. This task has some specific characteristics for images containing disjoint blobs. These images appear frequently in applications like cellular imaging, where it is often necessary to process them in large amounts. In such cases, achieving a high degree of automation becomes an important factor. When correcting uneven illumination by morphological processing for this class of images, selecting an appropriate size for the structuring element (SE) is a relevant issue. In this work, a method based in grayscale morphological operations is presented, to determine an appropriate size of the SE. The effectiveness of the method was tested through simulations using images derived from real world examples. Results are presented in terms of tables showing the precision in recovering the original image intensities, as well as through illustrative images.
Keywords
biology computing; cellular biophysics; image processing; cellular imaging; grayscale morphological operations; image intensities; image uneven illumination correction; morphological correction; morphological processing; nonuniform illumination; size determination method; structuring element; Conferences; Gray-scale; Image segmentation; Lighting; Microscopy; Transforms; Uneven illumination; morphological image processing;
fLanguage
English
Publisher
ieee
Conference_Titel
Image Processing (ICIP), 2011 18th IEEE International Conference on
Conference_Location
Brussels
ISSN
1522-4880
Print_ISBN
978-1-4577-1304-0
Electronic_ISBN
1522-4880
Type
conf
DOI
10.1109/ICIP.2011.6115715
Filename
6115715
Link To Document