View-Invariant Template Matching Using Homography Constraints
This addresses the challenge of object recognition across varying viewpoints for computer vision applications, but it is incremental as it builds on homography constraints without a paradigm shift.
The paper tackles the problem of view-invariant object recognition by proposing a method to match objects in images from different viewpoints without restrictions on camera parameters or prior 3D knowledge, achieving robustness to noise and performance in real-world applications like face and object recognition.
Change in viewpoint is one of the major factors for variation in object appearance across different images. Thus, view-invariant object recognition is a challenging and important image understanding task. In this paper, we propose a method that can match objects in images taken under different viewpoints. Unlike most methods in the literature, no restriction on camera orientations or internal camera parameters are imposed and no prior knowledge of 3D structure of the object is required. We prove that when two cameras take pictures of the same object from two different viewing angels, the relationship between every quadruple of points reduces to the special case of homography with two equal eigenvalues. Based on this property, we formulate the problem as an error function that indicates how likely two sets of 2D points are projections of the same set of 3D points under two different cameras. Comprehensive set of experiments were conducted to prove the robustness of the method to noise, and evaluate its performance on real-world applications, such as face and object recognition.