A Vision Based Method for Object Recognition

Recognizing objects in images is a very important research task in the field of computer vision and pattern recognition. We introduce an effective method for object recognition. In order to characterize the appearance of the objects, the SFIT features are extracted from the images. Then, these features are sent to train four classifiers i.e. KNN classifier, Naive Bayes classifier, Decision tree classifier and SVM classifier which are used to predict objects. Out method performs well on the Caltech image data in the experiments.