<fmt:message key='jsp.layout.header-default.alt'/>  
 

DSpace@UM >
Faculty of Computer Science and Information Technology >
Academic Exercise (Bachelor of Computer Science) >

Please use this identifier to cite or link to this item: http://hdl.handle.net/1812/815

Title: Object detection by using edge segmentation techniques
Authors: Hanisah Bt Zulkafli
Keywords: Object detection
Edge segmentation techniques
Image processing
Algorithm
Issue Date: 2009
Publisher: University of Malaya
Abstract: This paper will present the techniques on detecting the edge of the object that implemented in image processing environment. The purpose of this paper is to make an understanding how image processing dealing with certain object and recognize the shape of object and their contour, furthermore there are basic important that people must know how the image are being created. There are also applications that are required to implement those techniques to generate the object itself. While we know how the object will look likes, we must know the basic techniques that can implemented to the object and how the object can be created in digital image processing. The aim of this research is to have an algorithm on detecting an object in image by have the techniques on edge-based segmentation techniques. The detection of the edge is necessarily for the new object to be recognized. Edge detection techniques commonly use in multimedia field, which can be necessary to develop an image or make some adjustment on the image or the object. As we know, edge is defined as a step or as a slope between two uniform luminance areas. Actually, edges may deviate from these cases in many ways, in fact edges may be a gradual transaction between two areas of non-uniform intensity or between two areas of similar intensity, noisy or any combination of these.[19] Edges convey essential information to a picture, and their accurate detection is of primary importance. Therefore we need a technique to detect an object, as for that purpose, edge detection is one of the subjects of basic importance in image processing. Edge detection techniques transform images to edge images benefiting from the changes of grey tones in the images. There are many tools or system that being using by developer to develop an object and manipulate the object or sometimes we can call it as image by using software, such as MATLAB or SCION IMAGE software to encode the instruction to the image or do some function on that image require. The requirement of edge detection techniques will require a detector such as Sobel and Canny, which are the techniques that will use to detect an edge and also the object. The purpose of this research also to implement a technique on how to join gaps between edges detected by the object with a new algorithm that compose based on the Canny and Sobel detector but with a new approach techniques that will enhance image color. The delivering of this technology approach will deliver to audience such as, researchers that do their research on how to improve the object recognition, for lecturer that deliver their knowledge to student, which is for student to know how object will be recognize by use an image processing.
Description: Academic Exercise (B.C.S.) Faculty of Computer Science & Information Technology, University Malaya, 2009.
URI: http://dspace.fsktm.um.edu.my/handle/1812/815
Appears in Collections:Academic Exercise (Bachelor of Computer Science)

Files in This Item:

File Description SizeFormat
CHAPTER 4.pdfChapter 4106.39 kBAdobe PDFView/Open
CHAPTER 1.pdfChapter 1149 kBAdobe PDFView/Open
APPENDICES.pdf70.36 kBAdobe PDFView/Open
REFERENCES.pdf55.35 kBAdobe PDFView/Open
CHAPTER 8.pdfChapter 861.86 kBAdobe PDFView/Open
CHAPTER 3.pdfChapter 372.96 kBAdobe PDFView/Open
CHAPTER 7.pdfChapter 7254.02 kBAdobe PDFView/Open
COVER PAGE.pdf81.72 kBAdobe PDFView/Open
CHAPTER 2.pdfChapter 2271.22 kBAdobe PDFView/Open
ABSTRACT.pdf8.22 kBAdobe PDFView/Open
CHAPTER 5.pdfChapter 591.05 kBAdobe PDFView/Open
ACKNOWLEDGEMENT.pdf5.36 kBAdobe PDFView/Open
CHAPTER 6.pdfChapter 6847.46 kBAdobe PDFView/Open


This item is protected by original copyright



Their Tags: edge detection; internal segmentation;

Your Tags:

 

  © Copyright 2008 DSpace Faculty of Computer Science and Information Technology, University of Malaya . All Rights Reserved.
DSpace@UM is powered by MIT - Hawlett-Packard. More information and software credits. Feedback