Template Matching with Deformable Diversity Similarity
This work addresses template matching challenges in computer vision, offering a robust method for applications like object detection, but it appears incremental as it builds on existing feature-based approaches.
The authors tackled the problem of template matching under complex deformations, clutter, and occlusions by proposing a novel similarity measure based on feature match diversity, resulting in improved detection accuracy and computational efficiency on a benchmark.
We propose a novel measure for template matching named Deformable Diversity Similarity -- based on the diversity of feature matches between a target image window and the template. We rely on both local appearance and geometric information that jointly lead to a powerful approach for matching. Our key contribution is a similarity measure, that is robust to complex deformations, significant background clutter, and occlusions. Empirical evaluation on the most up-to-date benchmark shows that our method outperforms the current state-of-the-art in its detection accuracy while improving computational complexity.