Robust model-based scene interpretation by multilayered context information
Computer Vision and Image Understanding
SPIRE '09 Proceedings of the 16th International Symposium on String Processing and Information Retrieval
A PTAS for the square tiling problem
SPIRE'10 Proceedings of the 17th international conference on String processing and information retrieval
Robust click-point linking for longitudinal follow-up studies
Miar'06 Proceedings of the Third international conference on Medical Imaging and Augmented Reality
Journal of Discrete Algorithms
Transfer Learning from Unlabeled Data via Neural Networks
Neural Processing Letters
| Hi-index | 0.00 |
We describe a novel technique for identifying semantically equivalent parts in images belonging to the same object class, (e.g. eyes, license plates, aircraft wings etc.). The visual appearance of such object parts can differ substantially, and therefore traditional image similarity-based methods are inappropriate for this task. The technique we propose is based on the use of common context. We first retrieve context fragments, which consistently appear together with a given input fragment in a stable geometric relation. We then use the context fragments in new images to infer the most likely position of equivalent parts. Given a set of image examples of objects in a class, the method can automatically learn the part structure of the domain 驴 identify the main parts, and how their appearance changes across objects in the class. Two applications of the proposed algorithm are shown: the detection and identification of object parts and object recognition.