Object classification Techniques using Machine Learning Model

摘要

Detecting people in images is key for several important application domains in computer vision. This paper presents an indepth experimental study on pedestrian classification; multiple featureclassifier combinations are examined with respect to their performance and efficiency. In investigate global versus local, as exemplified by PCA coefficients. In terms of classifiers, consider the popular Support Vector Machines (SVMs), Adaptive boost with SVM. Experiments are performed on a large data set consisting of 4,000 pedestrian and more than statistically meaningful results are obtained by analysing performance variances caused by varying training and test sets. Furthermore, to investigate how classification performance and training sample size are correlated. Our experiments show that the novel combination of SVMs with Adaptive Boost.