Development Of Algorithm Of Classification Between Human And Non-Human

Ramiza , Mohd Yunus (2008) Development Of Algorithm Of Classification Between Human And Non-Human. Project Report. UTeM, Melaka,Malaysia. (Submitted)

	PDF (24 Pages) Development_Of_Algorithm_Of_Classification_Between_Human_And_Non-Human_Ramiza_Mohd_Yunus_TA1637.R35_2008_-_24_Pages.pdf - Submitted Version Download (215kB)
	PDF (Full Text) Development_Of_Algorithm_Of_Classification_Between_Human_And_Non-Human_Ramiza_Mohd_Yunus_TA1637.R35_2008.pdf - Submitted Version Restricted to Registered users only Download (1MB)

Abstract

Human detection has widely used in computer vision development. Classifying a moving object as a human or non-human has a practical value to apply in many areas for example security surveillance. This paper discussed the development of algorithm of classification between human and non-human using Support Vector Machine (SVM) to classify an image as a human or non-human. The software development using Support Vector Machine algorithm in MATLAB will be trained and tested to sets of images. Support Vector Machine is a set of related supervised learning methods for classification and regression. The images are evaluated using the algorithm which will construct separating hyperplane which maximize the margin between two data sets. The tested algorithm thus will process image input and decide which class the new image belongs to. This developed algorithm based on Support Vector Machine thus classifies the object in an image between human and non-human.

Actions (login required)

View Item