Combination of Global and Local Features for Efficient Classification of Paintings

Since the beginning of the new century an increasing amount of smartphones sold every year causes a strong interest in the interactive mobile guides (travel, museum guides) utilizing the visual recognition of interesting objects. In our paper we focus on a special class of objects -- fine art paintings. We introduce new pipeline of visual recognition employing both local and global image features. In the recognition process we firstly sort the database of Originals, the high quality paintings based on the global feature extracted from the photograph of a painting and then match the local feature descriptors for efficient recognition. Our approach achieves the speed up of the recognition process by minimizing the number local feature comparisons.