Please use this identifier to cite or link to this item:
Full metadata record
DC FieldValueLanguage
dc.coverage.spatialComputer Science and Engineeringen_US
dc.description.abstractClassification and recognition of objects is the interesting topic for newlinemany researchers. Shape is a significant feature of objects and it plays a newlinecrucial role in image classification and recognition. A good shape newlinerepresentation provides the foundation for the development of efficient newlinealgorithms for many shape related processing tasks, such as image newlinecoding, age classification, stone texture classification, character newlinerecognition, shape matching, object recognition, content based video newlineprocessing and image data retrieval. The present study assumes that newlinetexture is characterized not only by the grey value at a given pixel, but newlinealso by the grey value pattern in a neighborhood surrounding the pixel. newlineThese patterns form a shape. The ability to efficiently analyze and newlinedescribe these shapes is thus of fundamental importance in various newlineclassification issues of textures. newlineThe human face provides the observer, lot of information about newlinegender, age, health, emotion etc. That s why the facial images are studied newlineintensively in the literature for many applications like face recognition, newlinepredicting features of the faces, reconstructing faces from some newlineprescribed features, classifying gender, races and expressions from facial newlineimages, and so on. The human facial images can be characterized by newlinelocal structural features very well. The structural approaches like Local newlineBinary Patterns (LBP), Texture Units (TU) and textons convey so much newlinexii newlinediscriminant information of the local structure. Only few researchers newlineanalyzed what kind of patterns or shapes of the above structural newlineapproaches classify images in an efficient way. The present thesis newlineextended this and proposed methods that derive shape features based on newlineintegrated approaches using LBP, TU, Textons and GLCM etc. newlineThe present thesis integrated the LBP and textons, which are newlineconsidered as texture shape primitives, and derived complex shape newlinefeatures on them for an efficient age classification system. In newlinecontinuation to this shape features are exploited on textons and texture newlineorientation men_US
dc.format.extentxviii, 116 Pen_US
dc.relationNo.of references -91en_US
dc.titleEffective classification of image textures using shape features derived from structural approachesen_US
dc.creator.researcherP. Chandrasekhar Reddyen_US
dc.subject.keywordComputer Science and Engineeringen_US
dc.subject.keywordImage texturesen_US
dc.subject.keywordshape feature derived form structural approachesen_US
dc.description.noteconclusion-101-106, references-107-116en_US
dc.contributor.guideDr. B. Eswara Reddyen_US
dc.publisher.universityJawaharlal Nehru Technological University, Anantapuramen_US
dc.publisher.institutionDepartment of Computer Science and Engineeringen_US
Appears in Departments:Department of Computer Science and Engineering

Files in This Item:
File Description SizeFormat 
01_title.pdfAttached File31.24 kBAdobe PDFView/Open
02_certificate&declaration.pdf42.86 kBAdobe PDFView/Open
03_acknowledgement.pdf55.44 kBAdobe PDFView/Open
04_contents.pdf39.67 kBAdobe PDFView/Open
05_preface.pdf56.84 kBAdobe PDFView/Open
06_list oftables and figures.pdf60.65 kBAdobe PDFView/Open
07_chapter 1.pdf2.81 MBAdobe PDFView/Open
08_chapter 2.pdf155.01 kBAdobe PDFView/Open
09_chapter 3.pdf195.64 kBAdobe PDFView/Open
10_chapter 4.pdf423.76 kBAdobe PDFView/Open
11_chapter 5.pdf138.04 kBAdobe PDFView/Open
12_chapter 6.pdf133.9 kBAdobe PDFView/Open
13_chapter 7.pdf63.38 kBAdobe PDFView/Open
14_references.pdf209.05 kBAdobe PDFView/Open

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

Altmetric Badge: