Call For Paper Volume:4 Issue:10 Oct'2017 |

OBJECTS DETECTION USING GABOR FILTER AND LABELING IN REALTIME ENVIRONMENT

Publication Date :



Author(s) :

P.NALINI , P.NALINI , M.SUJATHA.


Volume/Issue :
Volume 3
,
Issue 2
(12 - )



Abstract :

The greatest challenge on monitoring characters from monocular video scene is to track targets under occlusion conditions. The system tracks people from a video sequence and is robust to varied lighting conditions and complex crowded scenes. The method effectively handles small occlusions and invokes a manual tracking procedure under severe occlusions. The system also computes other parameters like velocity, average number of people crossing the region, and maximum. This paper is based on classifications of the features of an object detected using Gabor filter feature extraction techniques in image processing. The feature vector based on Gabor filters used as the input of the classifier, which is a Feed Forward Neural Network (FFNN) on a reduced feature subspace learned by an approach simpler than Principal Component Analysis (PCA). The effectiveness of the proposed method is demonstrated by the experimental results on testing large number of images and comparisons with state of the art method. Object detection and recognition has many applications in a variety of fields such as security systems, video conferencing and identification


No. of Downloads :

8


Indexing

Web Design MymensinghPremium WordPress ThemesWeb Development

OBJECTS DETECTION USING GABOR FILTER AND LABELING IN REALTIME ENVIRONMENT

February 20, 2016