Paper Info
Title
Object Detection Using a Cascade of Classifiers
Abstract
Typical object detection systems work by training a classifier on features extracted at different scales ofan object. In this paper we investigate the performance of an object detection system in which different classifiers which are trained at various scales of an object are combined and compare the performance with a typical object detection system where a single classifier is trained for all the scales. The notion behind such an approach is that the features extracted over smaller scales give more object’s specific information whereas large scale features provide more contextual information. We trained different classifiers for different scales and combined their output to reach a decision about the existence of an object. Confidence rated Ada-boost is used to train the classifiers. It was found that training a single classifier for all the scales results in superior performance as compared to training different classifiers for each scale and than combining their results. We show our results on objects belonging to three categories in TUDarmstadt and one category in Caltech4 [1].
Year
DOI
Venue
2008
10.1109/DICTA.2008.55
DICTA
Keywords
Field
DocType
scales result,different scale,object detection system,single classifier,different classifier,object detection,ofan object,typical object detection system,contextual information,large scale feature,superior performance,pixel,feature extraction,ada boost,boosting,classification algorithms
Computer science,Random subspace method,Artificial intelligence,Classifier (linguistics),Object detection,Computer vision,AdaBoost,Pattern recognition,Feature extraction,Boosting (machine learning),Pixel,Statistical classification,Machine learning
Conference
Citations 
PageRank 
References 
0
0.34
10
Authors
2
Name
Order
Citations
PageRank
Nayyar Abbas Zaidi1919.88
David Suter2509.31