Wavelet-based Reflection Symmetry Detection via Textural and Color Histograms

TL;DR

This paper introduces a novel reflection symmetry detection method that combines edge-based features with textural and color information, outperforming existing local feature-based approaches in identifying global symmetries.

Contribution

The proposed scheme integrates Log-Gabor filter-based edge features with a voting mechanism using textural and color neighborhoods for improved symmetry detection.

Findings

Outperforms existing methods on multiple datasets

Effectively detects global symmetries in complex images

Utilizes combined textural and color information for robustness

Abstract

Symmetry is one of the significant visual properties inside an image plane, to identify the geometrically balanced structures through real-world objects. Existing symmetry detection methods rely on descriptors of the local image features and their neighborhood behavior, resulting incomplete symmetrical axis candidates to discover the mirror similarities on a global scale. In this paper, we propose a new reflection symmetry detection scheme, based on a reliable edge-based feature extraction using Log-Gabor filters, plus an efficient voting scheme parameterized by their corresponding textural and color neighborhood information. Experimental evaluation on four single-case and three multiple-case symmetry detection datasets validates the superior achievement of the proposed work to find global symmetries inside an image.