Wan Najwa, Wan Ismail (2009) Object detection system using haar-classifier. Faculty of Electrical & Electronic Engineering, Universiti Malaysia Pahang.
|
Pdf
OBJECT DETECTION SYSTEM USING HAAR CLASSIFIER.PDF Download (3MB) | Preview |
Abstract
The invention of new algorithms had encouraged to the reinforcement of image processing’s application. An algorithm for the design object detection systems is presented. Haar-classifier is utilized as the algorithms for this object detection system. The exertion of Haar-Classifier had boosted to the upgrade system which is faster and more accurate. In this system, Haar-Classifier is conjunct with the Adaboost machine learning algorithms wherefore the performance of the system is upgraded. Development of this project is categorized into two phase which are training phase and execution phase. Training phase use OpenCV utilities such as haartraining.exe to train the object by calculating the object’s weak constraints. This is for the purpose of finding the different features of the object of interest. The list of these weak constraints is converted to the xml file to be included in the coding which had been developed using Visual Studio 2005. The execution process will result on the detection process of object of interest. System will detect rounded image in any image which had been included in the system itself. Object detection system using Haar-classifier algorithm can perform best performance of high detection rate and high level of accuracy rate.
| Item Type: | Undergraduates Project Papers |
|---|---|
| Additional Information: | Project paper (Bachelor of Electrical Engineering (Electronics) Universiti Malaysia Pahang - 2009, NO.CD:3303 |
| Uncontrolled Keywords: | Detectors |
| Subjects: | T Technology > TK Electrical engineering. Electronics Nuclear engineering |
| Faculty/Division: | Faculty of Electrical & Electronic Engineering |
| Depositing User: | Rohaida Idaris |
| Date Deposited: | 02 Apr 2010 06:39 |
| Last Modified: | 18 Oct 2023 06:49 |
| URI: | http://umpir.ump.edu.my/id/eprint/321 |
| Download Statistic: | View Download Statistics |
Actions (login required)
 |
View Item |