Boundary extraction and corner point detection for map of kariah Kg. Bukit Kapar / 'Afina AmirHussin
Boundary extraction and corner point detection are basic step for many image processing applications including image enhancement, object detection and pattern recognition. Traditional learning-based boundary extraction algorithms classify each pixel edge separately and then get boundaries from the l...
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | English |
| Published: |
2019
|
| Subjects: | |
| Online Access: | http://ir.uitm.edu.my/id/eprint/25263/ http://ir.uitm.edu.my/id/eprint/25263/1/TD_%27AFINA%20AMIRHUSSIN%20CS%20R%2019_5.pdf |
| Summary: | Boundary extraction and corner point detection are basic step for many image processing applications including image enhancement, object detection and pattern recognition. Traditional learning-based boundary extraction algorithms classify each pixel edge separately and then get boundaries from the local decisions of a classifier. The purpose of study is to extract the boundary of image, find the corner point and compare between two algorithms. However, this study applied morphology operation to extract the boundary image by using erosion operation. Morphology is a broad set of binary image operations that process images based on shapes. Corners in images represent a lot of important information. Extracting corners accurately is significant to image processing, which can reduce much of the calculations. Furthermore, two widely feature detection algorithms, which is Harris Corner Detector and FAST Corner Detector are used to compare in terms of the amount of corner point detection and run time of processing. The study used the image of the map of Kariah Kampung Bukit Kapar, Kapar, Klang, Selangor. First, the image will be smooth for retouching and look soft in certain part or entire image. Second, reduce the noise of image to maintain the features of edges. Third, extract the boundary of image. Then, these algorithms have been applied on the image. It is conclude that the FAST algorithm is better than Harris algorithm in terms of the amount of corner point detection and run time. |
|---|