New Graph-based Features For Shape Recognition

TL;DR

This paper introduces a graph-based feature extraction method for shape recognition in computer vision, demonstrating robustness to noise, rotation, scale, and articulation, and outperforming pixel-based approaches on multiple benchmarks.

Contribution

The paper proposes a novel graph-based approach to shape recognition that captures topological and geometrical properties, improving robustness over traditional pixel-based methods.

Findings

Outperforms state-of-the-art on Kimia's, Tari56, Tetrapod, and Articulated datasets.

Robust to noise, rotation, scale, and articulation.

Provides detailed analysis of method's performance under various conditions.

Abstract

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.