Object Labeling for Recognition Using Vocabulary Trees

We propose an approach to object recognition using vocabulary tree which, instead of finding the closest image in the database to the given query image, finds object labels representing the most similar objects to the query image. We can also recognize object pose if pose labels are associated to the database images. Our approach to object recognition relies on creating a specific object or pose descriptor for each group of database images representing the same object or object pose. The quantitative analysis showed that this approach is more efficient, both in terms of precision and speed, compared to original image retrieval based on vocabulary tree. The experiments are performed for object recognition on two different databases and pose recognition using available face database.