New Graph-based Features For Shape Recognition
This addresses shape recognition for computer vision applications, offering an incremental improvement over pixel-based methods by enhancing robustness to common distortions.
The paper tackles shape recognition in computer vision by proposing graph-based features that capture topological and geometric properties, achieving robust performance against noise, rotation, scale variation, and articulation as confirmed by comparisons on benchmarks like Kimia's and Tari56.
Shape recognition is the main challenging problem in computer vision. Different approaches and tools are used to solve this problem. Most existing approaches to object recognition are based on pixels. Pixel-based methods are dependent on the geometry and nature of the pixels, so the destruction of pixels reduces their performance. In this paper, we study the ability of graphs as shape recognition. We construct a graph that captures the topological and geometrical properties of the object. Then, using the coordinate and relation of its vertices, we extract features that are robust to noise, rotation, scale variation, and articulation. To evaluate our method, we provide different comparisons with state-of-the-art results on various known benchmarks, including Kimia's, Tari56, Tetrapod, and Articulated dataset. We provide an analysis of our method against different variations. The results confirm our performance, especially against noise.