Volume : IV, Issue : X, October - 2015
A Novel Algorithm for Object Detection in Low Contrast Image and Recognition by SVM
Anita Gain, Dharmendra Roy
Abstract :
Detection of object by Low contrast images is a very crucial task in computer vision and machine learning. There are many existing methods are available but they take much time and results are not accurate. To address this problem here we proposed a novel algorithm. This algorithm mainly consist three phases. First, extraction of foreground region and generate a fine coarse region of interest of object. Second, calculate co –ordinates points of the boundary of object and plot 2–D histogram for extract shape feature vector. Third, feed this feature vector into SVM whether it is human being or non–human being. Experimental results of this algorithm demonstrate that it is robust enough to handle image of low contrast as well as normal light condition. This algorithm is used in surveillance system.
Keywords :
Background subtraction boundary detection centroid partition of image segmentation SVM classification feature vector extraction.
Article:
Download PDF
DOI : 10.36106/ijsr
Cite This Article:
Anita Gain, Dharmendra Roy A Novel Algorithm for Object Detection in Low Contrast Image and Recognition by SVM International Journal of Scientific Research, Vol : 4, Issue : 10 October 2015
Number of Downloads : 839
References :
Anita Gain, Dharmendra Roy A Novel Algorithm for Object Detection in Low Contrast Image and Recognition by SVM International Journal of Scientific Research, Vol : 4, Issue : 10 October 2015
Our Other Journals...
-
Indian Journal of
Applied Research Visit Website -
PARIPEX Indian Journal
of Research Visit Website -
Global Journal for
Research Analysis Visit Website