Please use this identifier to cite or link to this item: http://dspace.dtu.ac.in:8080/jspui/handle/repository/16161
Full metadata record
DC FieldValueLanguage
dc.contributor.authorTIWARI, RAM MUKUND-
dc.date.accessioned2018-08-21T12:28:59Z-
dc.date.available2018-08-21T12:28:59Z-
dc.date.issued2011-06-
dc.identifier.urihttp://dspace.dtu.ac.in:8080/jspui/handle/repository/16161-
dc.description.abstractThis paper proposes an approach to edge detection of blurred color images. The edge detector involves two phases –Deblurring of color image using wavelet and edge detection using bacteria foraging. Here deblurring is performed without estimating the imge blur. The deblurring algorithm performs deblurring in the spectrum domain. In edge detection process, we find out the edge pixels on the basis of intensity difference value of pixel in their 8-neighbourhood. First step is Chemotaxis step in which we calculate the eight directional nutrients in the form of intensity difference and find out the edge pixels in the neighborhood of bacteria. Next in the Elimination and Dispersal step if a bacterium found itself low on nutrients than it will be eliminated from its current location and dispersed to some other location. Now if we trace all the edge pixels, given by the movement of bacteria than we will get an image highlighted with all the associated edges. By using the proposed technique, a marked visible improvement in the important edges is observed on various test images over common edge detectors.en_US
dc.language.isoenen_US
dc.relation.ispartofseriesTD-763;-
dc.subjectFUZZY EDGE DETECTIONen_US
dc.subjectBLURRED IMAGEen_US
dc.subjectEDGE DETECTORSen_US
dc.subjectBACTERIA FORAGING MAJORen_US
dc.titleFUZZY EDGE DETECTION OF BLURRED IMAGE USING BACTERIA FORAGINGen_US
dc.typeThesisen_US
Appears in Collections:M.E./M.Tech. Information Technology

Files in This Item:
File Description SizeFormat 
front.pdf33.44 kBAdobe PDFView/Open
four_pages.pdf643.12 kBAdobe PDFView/Open
edge_fuzzy_bacterial.pdf1.57 MBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.