A SIFT Based Object Recognition using contextual information

while automated object recognition in natural scenes has been studied for long times, it still remains a challenging problem in machine vision, image processing andanalysis. Object recognition is classifying an unknown object into one of the set of specified categories. The main problem in objectrecognition begins from the several factors, scaling, rotation, distortion, illumination, occlusion etc. In this paper first, we apply Scale Invariant Feature Transform (SIFT) method onimage to extract primitive points and the corresponding descriptors. Then we represent the extracted descriptors in formof AG graphs. So scene image and the model of objects we have two different graphs refer to it as scene and model graph. Wesuggest using the relaxation labeling to match the scene andmodel graphs. The result of experiment shows that the use of contextual information improves the descriptor matching significantly.

کلیدواژه ها:

object recognition ، relaxation labeling ، SIFT ، attribute graph (AG) ، contextual information